Chelsea Finn

EDBT 2026 Demo / reviewers in the wild / expert

dblp:131/1783 · DBLP profile ↗

← Back

159ranked-venue papers

9as first author

105since 2021 · last 2025

0000-0001-6298-0874ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 157 · 9 first-author · 103 since 2021Systems, architecture and hardware · 24 · 2 first-author · 11 since 2021Graphics, computer vision, multimedia, augmented reality and games · 6 · 4 since 2021Human-computer interaction and ubiquitous computing · 3 · 3 since 2021

Year	Publication	Venue	Position
2025	PERSONA: A Reproducible Testbed for Pluralistic Alignment abstract The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the plurality of user opinions, instead reinforcing majority viewpoints and marginalizing minority perspectives. We introduce PERSONA, a reproducible test bed designed to evaluate and improve pluralistic alignment of LMs. We procedurally generate diverse user profiles from US census data, resulting in 1,586 synthetic personas with varied demographic and idiosyncratic attributes. We then generate a large-scale evaluation dataset containing 3,868 prompts and 317,200 feedback pairs obtained from our synthetic personas. Leveraging this dataset, we systematically evaluate LM capabilities in role-playing diverse users, verified through human judges, and the establishment of both a benchmark, PERSONA Bench, for pluralistic alignment approaches as well as an extensive dataset to create new and future benchmarks. Louis Castricato, Nathan Lile, Rafael Rafailov, Jan-Philipp Fränken, Chelsea Finn	COLING	5
2025	CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models abstract Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale data from both robotic and non-robotic sources, current VLAs primarily focus on direct input–output mappings, lacking the intermediate reasoning steps crucial for complex manipulation tasks. As a result, existing VLAs lack temporal planning or reasoning capabilities. In this paper, we introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs) by predicting future image frames autoregressively as visual goals before generating a short action sequence to achieve these goals. We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens. Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks. Videos are available at: https://cot-vla.github.io/. Yao Lu 0006, Moo Jin Kim, Zipeng Fu, Zhuoyang Zhang, Yecheng Wu, Zhaoshuo Li, Song Han 0003, Chelsea Finn, Ankur Handa, Tsung-Yi Lin, Gordon Wetzstein, Ming-Yu Liu 0001, Donglai Xiang	CVPR	10
2025	Range, not Independence, Drives Modularity in Biologically Inspired Representations abstract Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired networks---those that are nonnegative and energy efficient---modularise their representation of source variables (sources). We derive necessary and sufficient conditions on a sample of sources that determine whether the neurons in an optimal biologically-inspired linear autoencoder modularise. Our theory applies to any dataset, extending far beyond the case of statistical independence studied in previous work. Rather we show that sources modularise if their support is ``sufficiently spread''. From this theory, we extract and validate predictions in a variety of empirical studies on how data distribution affects modularisation in nonlinear feedforward and recurrent neural networks trained on supervised and unsupervised tasks. Furthermore, we apply these ideas to neuroscience data, showing that range independence can be used to understand the mixing or modularising of spatial and reward information in entorhinal recordings in seemingly conflicting experiments. Further, we use these results to suggest alternate origins of mixed-selectivity, beyond the predominant theory of flexible nonlinear classification. In sum, our theory prescribes precise conditions on when neural activities modularise, providing tools for inducing and elucidating modular representations in brains and machines. William Dorrell, Kyle Hsu, Luke Hollingsworth, Jin Hwa Lee, Jiajun Wu 0001, Chelsea Finn, Peter E. Latham, Timothy Edward John Behrens, James C. R. Whittington	ICLR	6
2025	Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval abstract The hallucinations of large language models (LLMs) are increasingly mitigated by allowing LLMs to search for information and to ground their answers in real sources. Unfortunately, LLMs often struggle with posing the right search queries, especially when dealing with complex or otherwise indirect topics. Observing that LLMs can learn to search for relevant facts by $\textit{trying}$ different queries and learning to up-weight queries that successfully produce relevant results, we introduce $\underline{Le}$arning to $\underline{Re}$trieve by $\underline{T}$rying (LeReT), a reinforcement learning framework that explores search queries and uses preference-based optimization to improve their quality. LeReT can improve the absolute retrieval accuracy by up to 29\% and the downstream generator evaluations by 17\%. The simplicity and flexibility of LeReT allows it to be applied to arbitrary off-the-shelf retrievers and makes it a promising technique for improving general LLM pipelines. Sheryl Hsu, Omar Khattab, Chelsea Finn, Archit Sharma	ICLR	3
2025	Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling abstract Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its effects on the learned policy remain inconsistent: some studies find it crucial for achieving strong results, while others observe decreased performance. In this paper, we first dissect how action chunking impacts the divergence between a learner and a demonstrator. We find that action chunking allows the learner to better capture the temporal dependencies in demonstrations but at the cost of reduced reactivity to unexpected states. To address this tradeoff, we propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation. At each timestep, BID samples multiple candidate predictions and searches for the optimal one based on two criteria: (i) backward coherence, which favors samples that align with previous decisions; (ii) forward contrast, which seeks samples of high likelihood for future plans. By coupling decisions within and across action chunks, BID promotes both long-term consistency and short-term reactivity. Experimental results show that our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks. Code and videos are available at https://bid-robot.github.io. Yuejiang Liu, Jubayer Ibn Hamid, Annie Xie, Yoonho Lee 0001, Maximilian Du, Chelsea Finn	ICLR	6
2025	Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models abstract Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions (e.g., "Could you make me a vegetarian sandwich?" or "I don’t like that one") require not just the ability to physically perform the individual steps, but the ability to situate complex commands and feedback in the physical world. In this work, we describe a system that uses vision-language models in a hierarchical structure, first reasoning over complex prompts and user feedback to deduce the most appropriate next step to fulfill the task, and then performing that step with low-level actions. In contrast to direct instruction following methods that can fulfill simple commands ("pick up the cup"), our system can reason through complex prompts and incorporate situated feedback during task execution ("that’s not trash"). We evaluate our system across three robotic platforms, including single-arm, dual-arm, and dual-arm mobile robots, demonstrating its ability to handle tasks such as cleaning messy tables, making sandwiches, and grocery shopping. Videos are available at https://www.pi.website/research/hirobot Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Drieß, Lachy Groom, Sergey Levine, Chelsea Finn	ICML	15
2025	Latent Diffusion Planning for Imitation Learning abstract Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations. To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoencoder, enabling effective forecasting of future states in image-based domains. Then, we train a planner and an inverse dynamics model with diffusion objectives. By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data. On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches, as they cannot leverage such additional data. Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn	ICML	4
2025	Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models abstract Legged robots are physically capable of navigating a diverse variety of environments and overcoming a wide range of obstructions. For example, in a search and rescue mission, a legged robot could climb over debris, crawl through gaps, and navigate out of dead ends. However, the robot's controller needs to respond intelligently to such varied obstacles, and this requires handling unexpected and unusual scenarios successfully. This presents an open challenge to current learning methods, which often struggle with generalization to the long tail of unexpected situations without heavy human supervision. To address this issue, we investigate how to leverage the broad knowledge about the structure of the world and commonsense reasoning capabilities of vision-language models (VLMs) to aid legged robots in handling difficult, ambiguous situations. We propose a system, VLM-Predictive Control (VLM-PC), combining two key components that we find to be crucial for eliciting on-the-fly, adaptive behavior selection with VLMs: (1) in-context adaptation over previous robot interactions and (2) planning multiple skills into the future and replanning. We evaluate VLMPC on several challenging real-world obstacle courses, involving dead ends and climbing and crawling, on a Go1 quadruped robot. Our experiments show that by reasoning over the history of interactions and future plans, VLMs enable the robot to autonomously perceive, navigate, and act in a wide range of complex scenarios that would otherwise require environmentspecific engineering or human guidance. Annie S. Chen, Alec M. Lessing, Andy Tang, Govind Chada, Laura Smith 0001, Sergey Levine, Chelsea Finn	ICRA	7
2025	RoboCrowd: Scaling Robot Data Collection Through Crowdsourcing abstract In recent years, imitation learning from large-scale human demonstrations has emerged as a promising paradigm for training robot policies. However, the burden of collecting large quantities of human demonstrations is significant in terms of collection time and the need for access to expert operators. We introduce a new data collection paradigm, RoboCrowd, which distributes the workload by utilizing crowdsourcing principles and incentive design. RoboCrowd helps enable scalable data collection and facilitates more efficient learning of robot policies. We build RoboCrowd on top of ALOHA [1]—a bimanual platform that supports data collection via puppeteering—to explore the design space for crowdsourcing in-person demonstrations in a public environment. We propose three classes of incentive mechanisms to appeal to users' varying sources of motivation for interacting with the system: material rewards, intrinsic interest, and social comparison. We instantiate these incentives through tasks that include physical rewards, engaging or challenging manipulations, as well as gamification elements such as a leaderboard. We conduct a large-scale, two-week field experiment in which the platform is situated in a university café. We observe significant engagement with the system—over 200 individuals independently volunteered to provide a total of over 800 interaction episodes. Our findings validate the proposed incentives as mechanisms for shaping users' data quantity and quality. Further, we demonstrate that the crowdsourced data can serve as useful pre-training data for policies fine-tuned on expert demonstrations—boosting performance up to 20 % compared to when this data is not available. These results suggest the potential for RoboCrowd to reduce the burden of robot data collection by carefully implementing crowdsourcing and incentive design principles. Videos are available at https://robocrowd.github.io. Suvir Mirchandani, David Yuan 0001, Kaylee Burns, Md Sazzad Islam, Tony Z. Zhao, Chelsea Finn, Dorsa Sadigh	ICRA	6
2025	Speedtuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning abstract While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds. Imitation learning policies are inherently limited by hardware constraints and the speed of the operator during data collection. In addition, there are no established methods for accelerating policies learned via imitation, and the empirical relationship between execution speed and task success remains underexplored. To address these issues, we introduce Speed Tuning, a reinforcement learning framework specifically designed to enhance the speed of manipulation policies. SPEEDTUNING learns to predict the optimal execution speed for actions, thereby complementing a base policy without necessitating additional data collection. We provide empirical evidence that SPEEDTUNING achieves substantial improvements in execution speed, exceeding 2.4x speed-up, while preserving an adequate success rate compared to both the original task policy and straightforward speed-up methods such as linear interpolation at a fixed speed. We evaluate our approach across a diverse set of dynamic and precise tasks, including pouring, throwing, and picking, demonstrating its effectiveness and robustness in enhancing real-world robotic manipulation. Videos and code are available at https://daivdyuan.github.io/speed-tuning/ David Yuan 0001, Tony Z. Zhao, Kaylee Burns, Chelsea Finn	ICRA	4
2025	Affordance-Guided Reinforcement Learning via Visual Prompting abstract Robots equipped with reinforcement learning (RL) have the potential to learn a wide range of skills solely from a reward signal. However, obtaining a robust and dense reward signal for general manipulation tasks remains a challenge. Existing learning-based approaches require significant data, such as human demonstrations of success and failure, to learn task-specific reward functions. Recently, there is also a growing adoption of large multi-modal foundation models for robotics that can perform visual reasoning in physical contexts and generate coarse robot motions for manipulation tasks. Motivated by this range of capability, in this work, we present Keypoint-based Affordance Guidance for Improvements (KAGI), a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL. State-of-the-art VLMs have demonstrated impressive zero-shot reasoning about affordances through keypoints, and we use these to define dense rewards that guide autonomous robotic learning. On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps. Additionally, we demonstrate the robustness of KAGI to reductions in the number of indomain demonstrations used for pre-training, reaching similar performance in 45K online fine-tuning steps.† Olivia Y. Lee, Annie Xie, Kuan Fang, Karl Pertsch, Chelsea Finn	IROS	5
2025	Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models abstract Learning-Based methods have achieved strong performance for quadrupedal locomotion. However, several challenges prevent quadrupeds from learning helpful indoor skills that require interaction with environments and humans: lack of end-effectors for manipulation, limited semantic under-standing using only simulation data, and low traversability and reachability in indoor environments. We present a system for quadrupedal mobile manipulation in indoor environments. It uses a front-mounted gripper for object manipulation, a low-level controller trained in simulation using egocentric depth for agile skills like climbing and whole-body tilting, and pre-trained vision-language models (VLMs) with a third-person fisheye and an egocentric RGB camera for semantic understanding and command generation. We evaluate our system in two unseen environments without any real-world data collection or training. Our system can zero-shot generalize to these environments and complete tasks, like following user’s commands to fetch a randomly placed stuff toy after climbing over a queen-sized bed, with a 60% success rate. Zipeng Fu, Xuxin Cheng, Xiaolong Wang 0004, Chelsea Finn	IROS	5
2025	MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation? abstract While text-to-image models like GPT-4o-Image and FLUX are rapidly proliferating, they often encounter challenges such as hallucination, bias, and the production of unsafe, low-quality output. To effectively address these issues, it is crucial to align these models with desired behaviors based on feedback from a multimodal judge. Despite their significance, current multimodal judges frequently undergo inadequate evaluation of their capabilities and limitations, potentially leading to misalignment and unsafe fine-tuning outcomes. To address this issue, we introduce MJ-Bench, a novel benchmark which incorporates a comprehensive preference dataset to evaluate multimodal judges in providing feedback for image generation models across six key perspectives: alignment, safety, image quality, bias, composition, and visualization. Specifically, we evaluate a large variety of multimodal judges including smaller-sized CLIP-based scoring models, open-source VLMs, and close-source VLMs on each decomposed subcategory of our preference dataset. Experiments reveal that close-source VLMs generally provide better feedback, with GPT-4o outperforming other judges in average. Compared with open-source VLMs, smaller-sized scoring models can provide better feedback regarding text-image alignment and image quality, while VLMs provide more accurate feedback regarding safety and generation bias due to their stronger reasoning capabilities. Further studies in feedback scale reveal that VLM judges can generally provide more accurate and stable feedback in natural language than numerical scales. Notably, human evaluations on end-to-end and fine-tuned models using separate feedback from these multimodal judges provide similar conclusions, further confirming the effectiveness of MJ-Bench. Zhaorun Chen, Zichen Wen, Yichao Du, Yiyang Zhou, Chenhang Cui, Siwei Han, Jen Weng, Chaoqi Wang, Zhengwei Tong, Leria Huang, Canyu Chen, Haoqin Tu, Qinghao Ye, Zhihong Zhu 0001, Zhuokai Zhao, Rafael Rafailov, Chelsea Finn, Huaxiu Yao	NeurIPS	19
2025	SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing abstract Robotic suturing is a prototypical long-horizon dexterous manipulation task, requiring coordinated needle grasping, precise tissue penetration, and secure knot tying. Despite numerous efforts toward end-to-end autonomy, a fully autonomous suturing pipeline has yet to be demonstrated on physical hardware. We introduce SutureBot: an autonomous suturing benchmark on the da Vinci Research Kit (dVRK), spanning needle pickup, tissue insertion, and knot tying. To ensure repeatability, we release a high-fidelity dataset comprising 1,890 suturing demonstrations. Furthermore, we propose a goal-conditioned framework that explicitly optimizes insertion-point precision, improving targeting accuracy by 59\%-74\% over a task-only baseline. To establish this task as a benchmark for dexterous imitation learning, we evaluate state-of-the-art vision-language-action (VLA) models, including $\pi_0$, GR00T N1, OpenVLA-OFT, and multitask ACT, each augmented with a high-level task-prediction policy. Autonomous suturing is a key milestone toward achieving robotic autonomy in surgery. These contributions support reproducible evaluation and development of precision-focused, long-horizon dexterous manipulation policies necessary for end-to-end suturing. Dataset is available at: \href{https://huggingface.co/datasets/jchen396/suturebot}{Hugging Face} Jesse Haworth, Juo-Tung Chen, Nigel Nelson, Ji Woong Kim, Masoud Moghani, Chelsea Finn, Axel Krieger	NeurIPS	6
2025	MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference abstract Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, content hallucination, safety concerns, and generation bias. To address these limitations, we introduce MJ-BENCH-VIDEO, a large-scale video preference benchmark designed to evaluate video generation across five critical aspects: Alignment, Safety, Fineness, Coherence & Consistency, and Bias & Fairness. This benchmark further incorporates 28 fine-grained criteria to provide a comprehensive evaluation of video preference. Building upon this dataset, we propose MJ-VIDEO, a Mixture-of-Experts (MoE)-based video reward model designed to deliver fine-grained reward. MJ-VIDEO can dynamically select relevant experts to accurately judge the preference based on the input text-video pair. This architecture enables more precise and adaptable preference judgments. Through extensive benchmarking on MJ-BENCH-VIDEO, we analyze the limitations of existing video reward models and demonstrate the superior performance of MJ-VIDEO in video preference assessment, achieving 17.58% and 15.87% improvements in overall and fine-grained preference judgments, respectively. Additionally, MJ-VIDEO is able to improve the alignment performance in video generation via preference fine-tuning. Haibo Tong, Zhaoyang Wang 0004, Zhaorun Chen, Haonian Ji, Shi Qiu 0016, Siwei Han, Kexin Geng, Zhongkai Xue, Yiyang Zhou, Peng Xia 0005, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao	NeurIPS	13
2024	PIGEON: Predicting Image Geolocations abstract Planet-scale image geolocalization remains a challenging problem due to the diversity of images originating from anywhere in the world. Although approaches based on vision transformers have made significant progress in ge-olocalization accuracy, success in prior literature is constrained to narrow distributions of images of landmarks, and performance has not generalized to unseen places. We present a new geolocalization system that combines semantic geocell creation, multitask contrastive pretraining, and a novel loss function. Additionally, our work is the first to perform retrieval over location clusters for guess refinements. We train two models for evaluations on street-level data and general-purpose image geolocalization; the first model, PIGEON, is trained on data from the game of Ge-oGuessr and is capable of placing over 40% of its guesses within 25 kilometers of the target location globally. We also develop a bot and deploy PIGEON in a blind experiment against humans, ranking in the top 0.01 % of players. We further challenge one of the world's foremost professional GeoGuessr players to a series of six matches with millions of viewers, winning all six games. Our second model, PI-GEOTTO, differs in that it is trained on a dataset of images from Flickr and Wikipedia, achieving state-of-the-art results on a wide range of image geolocalization benchmarks, outperforming the previous SOTA by up to 7.7 percentage points on the city accuracy level and up to 38.8 percentage points on the country level. Our findings suggest that PIGEOTTO is the first image geolocalization model that effectively generalizes to unseen places and that our approach can pave the way for highly accurate, planet-scale image geolocalization systems. Our code is available on GitHub.11https://github.com/LukasHaas/PIGEON Lukas Haas, Michal Skreta, Silas Alberti, Chelsea Finn	CVPR	4
2024	Calibrating Language Models with Adaptive Temperature Scaling abstract The effectiveness of large language models (LLMs) is not only measured by their ability to generate accurate outputs but also by their calibration-how well their confidence scores reflect the probability of their outputs being correct.While unsupervised pre-training has been shown to yield LLMs with well-calibrated conditional probabilities, recent studies have shown that after fine-tuning with reinforcement learning from human feedback (RLHF), the calibration of these models degrades significantly.In this work, we introduce Adaptive Temperature Scaling (ATS), a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction.The predicted temperature values adapt based on token-level features and are fit over a standard supervised fine-tuning (SFT) dataset.The adaptive nature of ATS addresses the varying degrees of calibration shift that can occur after RLHF fine-tuning.ATS improves calibration by over 10-50% across three downstream natural language evaluation benchmarks compared to prior calibration methods and does not impede performance improvements from RLHF. Johnathan Xie, Annie S. Chen, Yoonho Lee 0001, Eric Mitchell, Chelsea Finn	EMNLP	5
2024	Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models abstract If generalist robots are to operate in truly unstructured environments, they need to be able to recognize and reason about novel objects and scenarios. Such objects and scenarios might not be present in the robot’s own training data. We propose SuSIE, a method that leverages an image-editing diffusion model to act as a high-level planner by proposing intermediate subgoals that a low-level controller can accomplish. Specifically, we finetune InstructPix2Pix on video data, consisting of both human videos and robot rollouts, such that it outputs hypothetical future “subgoal” observations given the robot’s current observation and a language command. We also use the robot data to train a low-level goal-conditioned policy to act as the aforementioned low-level controller. We find that the high-level subgoal predictions can utilize Internet scale pretraining and visual understanding to guide the low-level goal-conditioned policy, achieving significantly better generalization and precision than conventional language-conditioned policies. We achieve state-of-the-art results on the CALVIN benchmark, and also demonstrate robust generalization on real-world manipulation tasks, beating strong baselines that have access to privileged information or that utilize orders of magnitude more compute and training data. The project website can be found at http://rail-berkeley.github.io/susie. Kevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Walke, Chelsea Finn, Aviral Kumar, Sergey Levine	ICLR	5
2024	Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features abstract Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts. In some situations, target data labels may be expensive to obtain, so we may only have access to a limited number of target data points. To make the most of a very small target dataset, we propose a lightweight, sample-efficient approach that learns a diverse set of features and adapts to a target distribution by interpolating these features. Our approach, Project and Probe (Pro$^2$), first learns a linear projection that maps a pre-trained embedding onto orthogonal directions while being predictive of labels in the source dataset. The goal of this step is to learn a variety of predictive features, so that at least some of them remain useful after distribution shift. Pro$^2$ then learns a linear classifier on top of these projected features using a small target dataset. Theoretically, we find that Pro$^2$ results in more sample-efficient generalization by inducing a favorable bias-variance tradeoff. Our experiments on four datasets, with multiple distribution shift settings for each, show that Pro$^2$ improves performance by 5-15% when given limited target data compared to prior methods such as standard linear probing. Annie S. Chen, Yoonho Lee 0001, Amrith Setlur, Sergey Levine, Chelsea Finn	ICLR	5
2024	RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches abstract Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a language-conditioned policy trained on pick-and-place tasks will not be able to generalize to a folding task, even if the arm trajectory of folding is similar to pick-and-place. Our key insight is that this kind of generalization becomes feasible if we represent the task through rough trajectory sketches. We propose a policy conditioning method using such rough trajectory sketches, which we call RT-Trajectory, that is practical, easy to specify, and allows the policy to effectively perform new tasks that would otherwise be challenging to perform. We find that trajectory sketches strike a balance between being detailed enough to express low-level motion-centric guidance while being coarse enough to allow the learned policy to interpret the trajectory sketch in the context of situational visual observations. In addition, we show how trajectory sketches can provide a useful interface to communicate with robotic policies -- they can be specified through simple human inputs like drawings or videos, or through automated methods such as modern image-generating or waypoint-generating methods. We evaluate RT-Trajectory at scale on a variety of real-world robotic tasks, and find that RT-Trajectory is able to perform a wider range of tasks compared to language-conditioned and goal-conditioned policies, when provided the same training data. Jiayuan Gu, Sean Kirmani, Paul Wohlhart, Yao Lu 0006, Montse Gonzalez Arenas, Kanishka Rao, Wenhao Yu 0003, Chuyuan Fu, Keerthana Gopalakrishnan, Priya Sundaresan, Peng Xu 0010, Hao Su 0001, Karol Hausman, Chelsea Finn, Ted Xiao	ICLR	15
2024	Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning abstract Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the model by optimizing the learned reward via reinforcement learning (RL). This paradigm assumes that human preferences are distributed according to reward, but recent work suggests that they instead follow the \emph{regret} under the user's optimal policy. Thus, learning a reward function from feedback is not only based on a flawed assumption of human preference, but also leads to unwieldy optimization challenges that stem from policy gradients or bootstrapping in the RL phase. Because of these optimization challenges, contemporary RLHF methods restrict themselves to contextual bandit settings (e.g., as in large language models) or limit observation dimensionality (e.g., state-based robotics). We overcome these limitations by introducing a new family of algorithms for optimizing behavior from human feedback using the \textit{regret}-based model of human preferences. Using the principle of maximum entropy, we derive \fullname (\abv), an algorithm for learning optimal policies from preferences without learning reward functions, circumventing the need for RL. \abv is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs. This enables \abv to elegantly scale to high-dimensional and sequential RLHF problems while being simpler than prior methods. Joey Hejna, Rafael Rafailov, Harshit Sikchi, Chelsea Finn, Scott Niekum, W. Bradley Knox, Dorsa Sadigh	ICLR	4
2024	An Emulator for Fine-tuning Large Language Models using Small Language Models abstract Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted examples or other specifications of desired behaviors. While it has been hypothesized that knowledge and skills come from pre-training, and fine-tuning mostly filters this knowledge and skillset, this intuition has not been extensively tested. To aid in doing so, we introduce a novel technique for decoupling the knowledge and skills gained in these two stages, enabling a direct answer to the question, What would happen if we combined the knowledge learned by a large model during pre-training with the knowledge learned by a small model during fine-tuning (or vice versa)? Using an RL-based framework derived from recent developments in learning from human preferences, we introduce emulated fine-tuning (EFT), a principled and practical method for sampling from a distribution that approximates (or 'emulates') the result of pre-training and fine-tuning at different scales. Our experiments with EFT show that scaling up fine-tuning tends to improve helpfulness, while scaling up pre-training tends to improve factuality. Beyond decoupling scale, we show that EFT enables test-time adjustment of competing behavioral traits like helpfulness and harmlessness without additional training. Finally, a special case of emulated fine-tuning, which we call LM up-scaling, avoids resource-intensive fine-tuning of large pre-trained models by ensembling them with small fine-tuned models, essentially emulating the result of fine-tuning the large pre-trained model. Up-scaling consistently improves helpfulness and factuality of instruction-following models in the Llama, Llama-2, and Falcon families, without additional hyperparameters or training. For reference implementation, see [https://github.com/eric-mitchell/emulated-fine-tuning](https://github.com/eric-mitchell/emulated-fine-tuning). Eric Mitchell, Rafael Rafailov, Archit Sharma, Chelsea Finn, Christopher D. Manning	ICLR	4
2024	Language Model Detectors Are Easily Optimized Against abstract The fluency and general applicability of large language models (LLMs) has motivated significant interest in detecting whether a piece of text was written by a language model. While both academic and commercial detectors have been deployed in some settings, particularly education, other research has highlighted the fragility of these systems. In this paper, we demonstrate a data-efficient attack that fine-tunes language models to confuse existing detectors, leveraging recent developments in reinforcement learning of language models. We use the `human-ness' score (often just a log probability) of various open-source and commercial detectors as a reward function for reinforcement learning, subject to a KL-divergence constraint that the resulting model does not differ significantly from the original. For a 7B parameter Llama-2 model, fine-tuning for under a day reduces the AUROC of the OpenAI RoBERTa-Large detector from 0.84 to 0.63, while perplexity on OpenWebText increases from 8.7 to only 9.0; with a larger perplexity budget, we can drive AUROC to 0.30 (worse than random). Similar to traditional adversarial attacks, we find that this increase in 'detector evasion' generalizes to other detectors not used during training. In light of our empirical results, we advise against continued reliance on LLM-generated text detectors. Models, datasets, and selected experiment code will be released at https://github.com/charlottttee/llm-detector-evasion. Charlotte Nicks, Eric Mitchell, Rafael Rafailov, Archit Sharma, Christopher D. Manning, Chelsea Finn, Stefano Ermon	ICLR	6
2024	Fine-Tuning Language Models for Factuality abstract The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as `hallucinations.' These errors can inadvertently spread misinformation or harmfully perpetuate misconceptions. Further, manual fact-checking of model responses is a time-consuming process, making human factuality labels expensive to acquire. In this work, we fine-tune language models to be more factual, without human labeling and targeting more open-ended generation settings than past work. We leverage two key recent innovations in NLP to do so. First, several recent works have proposed methods for judging the factuality of open-ended text by measuring consistency with an external knowledge base or simply a large model's confidence scores. Second, the Direct Preference Optimization algorithm enables straightforward fine-tuning of language models on objectives other than supervised imitation, using a preference ranking over possible model responses. We show that learning from automatically generated factuality preference rankings, generated either through existing retrieval systems or our novel retrieval-free approach, significantly improves the factuality (percent of generated claims that are correct) of Llama-2 on held-out topics compared with RLHF or decoding strategies targeted at factuality. At 7B scale, compared to Llama-2-Chat, we observe 53% and 50% reduction in factual error rate when generating biographies and answering medical questions, respectively. A reference implementation can be found at https://github.com/kttian/llm_factuality_tuning. Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning, Chelsea Finn	ICLR	5
2024	Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning abstract Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of existing methods are tailored to each domain, such as domain-specific augmentations which reflect the invariances in the target task. While masked modeling is promising as a domain-agnostic framework for self-supervised learning because it does not rely on input augmentations, its mask sampling procedure remains domain-specific. We present Self-guided Masked Autoencoders (SMA), a fully domain-agnostic masked modeling method. SMA trains an attention based model using a masked modeling objective, by learning masks to sample without any domain-specific assumptions. We evaluate SMA on three self-supervised learning benchmarks in protein biology, chemical property prediction, and particle physics. We find SMA is capable of learning representations without domain-specific knowledge and achieves state-of-the-art performance on these three benchmarks. Johnathan Xie, Yoonho Lee 0001, Annie S. Chen, Chelsea Finn	ICLR	4
2024	Improving Domain Generalization with Domain Relations abstract Distribution shift presents a significant challenge in machine learning, where models often underperform during the test stage when faced with a different distribution than the one they were trained on. In this paper, we focus on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on, and propose a new approach called DG. Unlike previous approaches that aim to learn a single model that is domain invariant, DG leverages domain similarities based on domain metadata to learn domain-specific models. Concretely, DG learns a set of training-domain-specific functions during the training stage and reweights them based on domain relations during the test stage. These domain relations can be directly obtained and learned from domain metadata. Under mild assumptions, we theoretically prove that using domain relations to reweight training-domain-specific functions achieves stronger out-of-domain generalization compared to the conventional averaging approach. Empirically, we evaluate the effectiveness of DG using both toy and real-world datasets for tasks such as temperature regression, land use classification, and molecule-protein binding affinity prediction. Our results show that DG consistently outperforms state-of-the-art methods. Huaxiu Yao, Xinyu Yang 0002, Xinyi Pan, Shengchao Liu, Pang Wei Koh, Chelsea Finn	ICLR	6
2024	Analyzing and Mitigating Object Hallucination in Large Vision-Language Models abstract Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating descriptions that include objects that do not actually exist in the images. This can negatively impact many vision-language tasks, such as visual summarization and reasoning. To address this issue, we propose a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions. LURE is grounded in a rigorous statistical analysis of the key factors underlying object hallucination, including co-occurrence (the frequent appearance of certain objects alongside others in images), uncertainty (objects with higher uncertainty during LVLM decoding), and object position (hallucination often appears in the later part of the generated text). LURE can also be seamlessly integrated with any LVLMs. We evaluate LURE on six open-source LVLMs and found it outperforms the previous best approach in both general object hallucination evaluation metrics, GPT, and human evaluations. Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, Huaxiu Yao	ICLR	6
2024	Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning abstract Inductive biases are crucial in disentangled representation learning for narrowing down an underspecified solution set. In this work, we consider endowing a neural network autoencoder with three select inductive biases from the literature: data compression into a grid-like latent space via quantization, collective independence amongst latents, and minimal functional influence of any latent on how other latents determine data generation. In principle, these inductive biases are deeply complementary: they most directly specify properties of the latent space, encoder, and decoder, respectively. In practice, however, naively combining existing techniques instantiating these inductive biases fails to yield significant benefits. To address this, we propose adaptations to the three techniques that simplify the learning problem, equip key regularization terms with stabilizing invariances, and quash degenerate incentives. The resulting model, Tripod, achieves state-of-the-art results on a suite of four image disentanglement benchmarks. We also verify that Tripod significantly improves upon its naive incarnation and that all three of its "legs" are necessary for best performance. Kyle Hsu, Jubayer Ibn Hamid, Kaylee Burns, Chelsea Finn, Jiajun Wu 0001	ICML	4
2024	PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs abstract Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs produce only textual outputs, while robotic control and other spatial tasks require outputting continuous coordinates, actions, or trajectories. How can we enable VLMs to handle such settings without fine-tuning on task-specific data? In this paper, we propose a novel visual prompting approach for VLMs that we call Prompting with Iterative Visual Optimization (PIVOT), which casts tasks as iterative visual question answering. In each iteration, the image is annotated with a visual representation of proposals that the VLM can refer to (e.g., candidate robot actions, localizations, or trajectories). The VLM then selects the best ones for the task. These proposals are iteratively refined, allowing the VLM to eventually zero in on the best available answer. We investigate PIVOT on real-world robotic navigation, real-world manipulation from images, instruction following in simulation, and additional spatial inference tasks such as localization. We find, perhaps surprisingly, that our approach enables zero-shot control of robotic systems without any robot training data, navigation in a variety of environments, and other capabilities. Although current performance is far from perfect, our work highlights potentials and limitations of this new regime and shows a promising approach for Internet-Scale VLMs in robotic and spatial reasoning domains. Soroush Nasiriany, Fei Xia 0002, Wenhao Yu 0003, Ted Xiao, Jacky Liang, Ishita Dasgupta 0001, Annie Xie, Danny Drieß, Ayzaan Wahid, Tingnan Zhang, Tsang-Wei Edward Lee, Kuang-Huei Lee, Peng Xu 0010, Sean Kirmani, Yuke Zhu, Andy Zeng 0001, Karol Hausman, Nicolas Heess, Chelsea Finn, Sergey Levine, Brian Ichter	ICML	21
2024	RLVF: Learning from Verbal Feedback without Overgeneralization abstract The diversity of contexts in which large language models (LLMs) are deployed requires the ability to modify or customize default model behaviors to incorporate nuanced requirements and preferences. A convenient interface to specify such model adjustments is high-level verbal feedback, such as “Don’t use emojis when drafting emails to my boss.” However, while writing high-level feedback is far simpler than collecting annotations for reinforcement learning from human feedback (RLHF), we find that simply prompting a model with such feedback leads to $\textbf{overgeneralization}$–applying feedback in contexts where it is not relevant. We propose a new method Contextualized Critiques with Constrained Preference Optimization (C3PO) to learn from high-level verbal feedback while reducing overgeneralization compared to current work. C3PO uses a piece of high-level feedback to generate a small synthetic preference dataset to specify when and how the feedback should (and should not) be applied. It then fine-tunes the model in accordance with the synthetic preference data while minimizing the divergence from the original model for prompts where the feedback does not apply. Our experimental results indicate that our approach effectively applies verbal feedback to relevant scenarios while preserving existing behaviors for other contexts more than current methods. For both human- and GPT-4-generated high-level feedback, C3PO effectively adheres to the given feedback comparably to in-context baselines while reducing overgeneralization by 30%. Moritz Stephan, Alexander Khazatsky, Eric Mitchell, Annie S. Chen, Sheryl Hsu, Archit Sharma, Chelsea Finn	ICML	7
2024	Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data abstract Learning from preference labels plays a crucial role in fine-tuning large language models — this is done via supervised learning, on-policy reinforcement learning (RL), or contrastive learning. Different methods come with different implementation tradeoffs, and existing empirical findings present different conclusions, for instance, some results show that online RL is quite important to attain good fine-tuning results, while others find offline methods sufficient. This raises a question: what kind of approaches are important for fine-tuning with preference data and why? In this paper, we answer this question by performing a rigorous analysis of a number of fine-tuning techniques on didactic and full-scale LLM problems. Our main finding is that approaches that use on-policy sampling and attempt to push down the likelihood on certain responses (i.e., employ a ”negative gradient”) outperform offline and maximum likelihood objectives. We conceptualize our insights and unify methods that use on-policy sampling or negative gradient under a notion of mode-seeking objectives for categorical distributions. Mode-seeking objectives are able to alter probability mass on specific bins of a categorical distribution at a fast rate compared to maximum likelihood, allowing them to relocate masses across bins more effectively. Our analysis prescribes actionable insights for preference fine-tuning of LLMs and informs how data should be collected for maximal improvement. Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff G. Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar	ICML	8
2024	Learning to Explore in POMDPs with Informational Rewards abstract Standard exploration methods typically rely on random coverage of the state space or coverage-promoting exploration bonuses. However, in partially observed settings, the biggest exploration challenge is often posed by the need to discover information-gathering strategies—e.g., an agent that has to navigate to a location in traffic might learn to first check traffic conditions and then choose a route. In this work, we design a POMDP agent that gathers information about the hidden state, using ideas from the meta-exploration literature. Our approach provides an exploration bonus that rewards the agent for gathering information about the state that is relevant for completing the task. While this requires the agent to know what this information is during training, it can obtained in several ways: in the most general case, off-policy algorithms can leverage knowledge about the entire trajectory to determine such information in hindsight, but the user can also provide prior knowledge (e.g., privileged information) to help inform the training process. Through experiments in several partially-observed environments, we find that our approach is competitive with prior methods when minimal exploration is needed, but substantially outperforms them when more complex strategies are required. Our algorithm also shows the ability to learn without any privileged information, by reasoning about the entire trajectory in hindsight and and effectively using any information it reveals about the hidden state. Annie Xie, Logan M. Bhamidipaty, Evan Zheran Liu, Joey Hong, Sergey Levine, Chelsea Finn	ICML	6
2024	SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning abstract In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as demonstrations and prior experience. However, despite these advances, robotic RL remains hard to use. It is acknowledged among practitioners that the particular implementation details of these algorithms are often just as important (if not more so) for performance as the choice of algorithm. We posit that a significant challenge to the widespread adoption of robotic RL, as well as the further development of robotic RL methods, is the comparative inaccessibility of such methods. To address this challenge, we developed a carefully implemented library containing a sample efficient off-policy deep RL method, together with methods for computing rewards and resetting the environment, a high-quality controller for a widely adopted robot, and a number of challenging example tasks. We provide this library as a resource for the community, describe its design choices, and present experimental results. Perhaps surprisingly, we find that our implementation can achieve very efficient learning, acquiring policies for PCB board assembly, cable routing, and object relocation between 25 to 50 minutes of training per policy on average, improving over state-of-the-art results reported for similar tasks in the literature. These policies achieve perfect or near-perfect success rates, extreme robustness even under perturbations, and exhibit emergent recovery and correction behaviors. We hope these promising results and our high-quality open-source implementation will provide a tool for the robotics community to facilitate further developments in robotic RL. Our code, documentation, and videos can be found at https://serl-robot.github.io/ Jianlan Luo, Zheyuan Hu 0003, Charles Xu 0003, You Liang Tan, Jacob Berg, Archit Sharma, Stefan Schaal, Chelsea Finn, Abhishek Gupta 0004, Sergey Levine	ICRA	8
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	38
2024	Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation abstract What makes generalization hard for imitation learning in visual robotic manipulation? This question is difficult to approach at face value, but the environment from the perspective of a robot can often be decomposed into enumerable factors of variation, such as the lighting conditions or the placement of the camera. Empirically, generalization to some of these factors have presented a greater obstacle than others, but existing work sheds little light on precisely how much each factor contributes to the generalization gap. Towards an answer to this question, we study imitation learning policies in simulation and on a real robot language-conditioned manipulation task to quantify the difficulty of generalization to different (sets of) factors. We design a simulated benchmark of 19 tasks with 11 factors of variation to facilitate more controlled evaluations of generalization. From our study, we determine an ordering of factors based on generalization difficulty, that is consistent across simulation and our real robot setup.1 Annie Xie, Lisa Lee, Ted Xiao, Chelsea Finn	ICRA	4
2024	Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning abstract The pre-train and fine-tune paradigm in machine learning has had dramatic success in a wide range of domains because the use of existing data or pre-trained models on the internet enables quick and easy learning of new tasks. We aim to enable this paradigm in robotic reinforcement learning, allowing a robot to learn a new task with little human effort by leveraging data and models from the Internet. However, reinforcement learning often requires significant human effort in the form of manual reward specification or environment resets, even if the policy is pre-trained. We introduce RoboFuME, a reset-free fine-tuning system that pre-trains a multi-task manipulation policy from diverse datasets of prior experiences and self-improves online to learn a target task with minimal human intervention. Our insights are to utilize calibrated offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy in the presence of distribution shifts and leverage pre-trained vision language models (VLMs) to build a robust reward classifier for autonomously providing reward signals during the online fine-tuning process. In a diverse set of five real robot manipulation tasks, we show that our method can incorporate data from an existing robot dataset collected at a different institution and improve on a target task within as little as 3 hours of autonomous real-world experience. We also demonstrate in simulation experiments that our method outperforms prior works that use different RL algorithms or different approaches for predicting rewards. Project website: https://robofume.github.io Max Sobol Mark, Brandon Vu, Archit Sharma, Jeannette Bohg, Chelsea Finn	ICRA	6
2024	Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms abstract Reinforcement Learning from Human Feedback (RLHF)has been crucial to the recent success of Large Language Models (LLMs), however it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represent human preferences, which is in turn used by an online reinforcement learning (RL) algorithm to optimized the LLM. A prominent issue with such methods is reward over-optimization or reward hacking, where the performance as measured by the learned proxy reward model increases, but the true model quality plateaus or even deteriorates. Direct Alignment Algorithms (DDAs), such as Direct Preference Optimization (DPO) have emerged as alternatives to the classical RLHF pipeline. However, despite not training a separate proxy reward model or using RL, they still commonly deteriorate from over-optimization. While the so-called reward hacking phenomenon is not well-defined for DAAs, we still uncover similar trends: at higher KL-budgets, DAA algorithms exhibit similar degradation patters to their classic RLHF counterparts. In particular, we find that DAA methods deteriorate not only across a wide range of KL-budgets, but also often before even a single epoch of the dataset is completed. Through extensive empirical experimentation this work formulates the reward over-optimization or hacking problem for DAAs and explores its consequences across objectives, training regimes, and model scales. Rafael Rafailov, Yaswanth Chittepu, Ryan Park, Harshit Sikchi, Joey Hejna, W. Bradley Knox, Chelsea Finn, Scott Niekum	NeurIPS	7
2024	A Critical Evaluation of AI Feedback for Aligning Large Language Models abstract Learning from AI feedback (LAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. LAIF first performs supervised fine-tuning (SFT) using demonstrations from a teacher model and then further fine-tunes the model with reinforcement learning (RL) or direct preference optimization (DPO), using feedback from a critic model. While recent popular open-source models have demonstrated substantial improvements in performance from the RL step, in this paper we question whether the complexity of this RL step is truly warranted for AI feedback. We show that the improvements of the RL step are virtually entirely due to the widespread practice of using a weaker teacher model (e.g. GPT-3.5) for SFT data collection than the critic (e.g., GPT-4) used for AI feedback generation. Specifically, we show that simple supervised fine-tuning with GPT-4 as the teacher outperforms existing LAIF pipelines. More generally, we find that the gains from LAIF vary substantially across base model families, test-time evaluation protocols, and critic models. Finally, we provide a mechanistic explanation for when SFT may outperform the full two-step LAIF pipeline as well as suggestions for making LAIF maximally useful in practice. Archit Sharma, Sedrick Keh, Eric Mitchell, Chelsea Finn, Kushal Arora, Thomas Kollar	NeurIPS	4
2024	Universal Neural Functionals abstract A challenging problem in many modern machine learning tasks is to process weight-space features, i.e., to transform or extract information from the weights and gradients of a neural network. Recent works have developed promising weight-space models that are equivariant to the permutation symmetries of simple feedforward networks. However, they are not applicable to general architectures, since the permutation symmetries of a weight space can be complicated by recurrence or residual connections. This work proposes an algorithm that automatically constructs permutation equivariant models, which we refer to as universal neural functionals (UNFs), for any weight space. Among other applications, we demonstrate how UNFs can be substituted into existing learned optimizer designs, and find promising improvements over prior methods when optimizing small image classifiers and language models. Our results suggest that learned optimizers can benefit from considering the (symmetry) structure of the weight space they optimize. Allan Zhou, Chelsea Finn, James Harrison	NeurIPS	2
2024	A Fast and Accurate Machine Learning Autograder for the Breakout Assignment abstract In this paper, we detail the successful deployment of a machine learning autograder that significantly decreases the grading labor required in the Breakout computer science assignment. This assignment - which tasks students with programming a game consisting of a controllable paddle and a ball that bounces off the paddle to break bricks - is popular for engaging students with introductory computer science concepts, but creates a large grading burden. Due to the game's interactive nature, grading defies traditional unit tests and instead typically requires 8+ minutes of manually playing each student's game to search for bugs. This amounts to 45+ hours of grading in a standard course offering and prevents further widespread adoption of the assignment. Our autograder alleviates this burden by playing each student's game with a reinforcement learning agent and providing videos of discovered bugs to instructors. In an A/B test with manual grading, we find that our human-in-the-loop AI autograder reduces grading time by 44%, while slightly improving grading accuracy by 6%, ultimately saving roughly 30 hours over our deployment in two offerings of the assignment. Our results further suggest the practicality of grading other interactive assignments (e.g., other games or building websites) via similar machine learning techniques. Live demo at https://ezliu.github.io/breakoutgrader. Evan Zheran Liu, David Yuan 0001, Elyse Cornwall, Juliette Woodrow, Kaylee Burns, Allen Nie, Emma Brunskill, Chris Piech, Chelsea Finn	SIGCSE (1)	10
2024	Clarify: Improving Model Robustness With Natural Language Corrections abstract The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide additional information beyond the training data. Prior methods incorporate additional instance-level supervision, such as labels for misleading features or additional labels for debiased data. However, such strategies require a large amount of labeler effort. We hypothesize that people are good at providing textual feedback at the concept level, a capability that existing teaching frameworks do not leverage. We propose Clarify, a novel interface and method for interactively correcting model misconceptions. Through Clarify, users need only provide a short text description of a model’s consistent failure patterns. Then, in an entirely automated way, we use such descriptions to improve the training process. Clarify is the first end-to-end system for user model correction. Our user studies show that non-expert users can successfully describe model misconceptions via Clarify, leading to increased worst-case performance in two datasets. We additionally conduct a case study on a large-scale image dataset, ImageNet, using Clarify to find and rectify 31 novel hard subpopulations. Yoonho Lee 0001, Michelle S. Lam, Helena Vasconcelos, Michael S. Bernstein, Chelsea Finn	UIST	5
2024	Bayesian Embeddings for Few-Shot Open World Recognition abstract As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from small amounts of information. This stands in stark contrast to modern machine learning systems that are typically designed with a known set of classes and a large number of examples for each class. In this work we extend embedding-based few-shot learning algorithms to the open-world recognition setting. We combine Bayesian non-parametric class priors with an embedding-based pre-training scheme to yield a highly flexible framework which we refer to as few-shot learning for open world recognition (FLOWR). We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets. Our results show, compared to prior methods, strong classification accuracy performance and up to a 12% improvement in H-measure (a measure of novel class detection) from our non-parametric open-world few-shot learning scheme. John Willes, James Harrison, Ali Harakeh, Chelsea Finn, Marco Pavone 0001, Steven Lake Waslander	IEEE Trans. Pattern Anal. Mach. Intell.	4
2023	Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models abstract A growing ecosystem of large, open-source foundation models has reduced the labeled data and technical expertise necessary to apply machine learning to many new problems. Yet foundation models pose a clear dual-use risk, indiscriminately reducing the costs of building both harmful and beneficial machine learning systems. Policy tools such as restricted model access and export controls are the primary methods currently used to mitigate such dual-use risks. In this work, we review potential safe-release strategies and argue that both policymakers and AI researchers would benefit from fundamentally new technologies enabling more precise control over the downstream usage of open-source foundation models. We propose one such approach: the task blocking paradigm, in which foundation models are trained with an additional mechanism to impede adaptation to harmful tasks without sacrificing performance on desirable tasks. We call the resulting models self-destructing models, inspired by mechanisms that prevent adversaries from using tools for harmful purposes. We present an algorithm for training self-destructing models leveraging techniques from meta-learning and adversarial learning, which we call meta-learned adversarial censoring (MLAC). In a small-scale experiment, we show MLAC can largely prevent a BERT-style model from being re-purposed to perform gender identification without harming the model’s ability to perform profession classification. Peter Henderson 0002, Eric Mitchell, Christopher D. Manning, Daniel Jurafsky, Chelsea Finn	AIES	5
2023	NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis abstract Expert demonstrations are a rich source of supervision for training visual robotic manipulation policies, but imitation learning methods often require either a large number of demonstrations or expensive online expert supervision to learn reactive closed-loop behaviors. In this work, we introduce SPARTN (Synthetic Perturbations for Augmenting Robot Trajectories via NeRF): a fully-offline data augmentation scheme for improving robot policies that use eye-in-hand cameras. Our approach leverages neural radiance fields (NeRFs) to synthetically inject corrective noise into visual demonstrations, using NeRFs to generate perturbed viewpoints while simultaneously calculating the corrective actions. This requires no additional expert supervision or environment interaction, and distills the geometric information in NeRFs into a real-time reactive RGB-only policy. In a simulated 6-DoF visual grasping benchmark, SPARTN improves success rates by 2.8× over imitation learning without the corrective augmentations and even outperforms some methods that use online supervision. It additionally closes the gap between RGB-only and RGB-D success rates, eliminating the previous need for depth sensors. In real-world 6-DoF robotic grasping experiments from limited human demonstrations, our method improves absolute success rates by 22.5% on average, including objects that are traditionally challenging for depth-based methods. See video results at https://bland.website/spartn. Allan Zhou, Moo Jin Kim, Lirui Wang, Peter R. Florence, Chelsea Finn	CVPR	5
2023	Meta-Learning Online Adaptation of Language Models abstract Large language models encode impressively broad world knowledge in their parameters.However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life."While online fine-tuning can reduce this degradation, we find that naively fine-tuning on a stream of documents leads to a low level of information uptake.We hypothesize that online fine-tuning does not sufficiently attend to important information.That is, the gradient signal from important tokens representing factual information is drowned out by the gradient from inherently noisy tokens, suggesting that a dynamic, context-aware learning rate may be beneficial.We therefore propose learning which tokens to upweight.We meta-train a small, autoregressive model to reweight the language modeling loss for each token during online fine-tuning, with the objective of maximizing the out-ofdate base question-answering model's ability to answer questions about a document after a single weighted gradient step.We call this approach Context-aware Meta-learned Loss Scaling (CaMeLS).Across three different distributions of documents, our experiments find that CaMeLS provides substantially improved information uptake on streams of thousands of documents compared with standard fine-tuning and baseline heuristics for reweighting token losses. Nathan Hu, Eric Mitchell, Christopher D. Manning, Chelsea Finn	EMNLP	4
2023	Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback abstract Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher Manning. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023. Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher D. Manning	EMNLP	7
2023	Surgical Fine-Tuning Improves Adaptation to Distribution Shifts Yoonho Lee 0001, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn	ICLR	7
2023	Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement Yoonho Lee 0001, Huaxiu Yao, Chelsea Finn	ICLR	3
2023	Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts Amrith Setlur, Don Kurian Dennis, Benjamin Eysenbach, Aditi Raghunathan, Chelsea Finn, Virginia Smith, Sergey Levine	ICLR	5
2023	A Control-Centric Benchmark for Video Prediction Stephen Tian, Chelsea Finn, Jiajun Wu 0001	ICLR	2
2023	Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning abstract Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated by this observation, we ask: can embodied reinforcement learning (RL) agents also indirectly learn language from non-language tasks? Learning to associate language with its meaning requires a dynamic environment with varied language. Therefore, we investigate this question in a multi-task environment with language that varies across the different tasks. Specifically, we design an office navigation environment, where the agent’s goal is to find a particular office, and office locations differ in different buildings (i.e., tasks). Each building includes a floor plan with a simple language description of the goal office’s location, which can be visually read as an RGB image when visited. We find RL agents indeed are able to indirectly learn language. Agents trained with current meta-RL algorithms successfully generalize to reading floor plans with held-out layouts and language phrases, and quickly navigate to the correct office, despite receiving no direct language supervision. Evan Zheran Liu, Sahaana Suri, Tong Mu, Allan Zhou, Chelsea Finn	ICML	5
2023	DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature abstract The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text. In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection. Specifically, we demonstrate that text sampled from an LLM tends to occupy negative curvature regions of the model's log probability function. Leveraging this observation, we then define a new curvature-based criterion for judging if a passage is generated from a given LLM. This approach, which we call DetectGPT, does not require training a separate classifier, collecting a dataset of real or generated passages, or explicitly watermarking generated text. It uses only log probabilities computed by the model of interest and random perturbations of the passage from another generic pre-trained language model (e.g., T5). We find DetectGPT is more discriminative than existing zero-shot methods for model sample detection, notably improving detection of fake news articles generated by 20B parameter GPT-NeoX from 0.81 AUROC for the strongest zero-shot baseline to 0.95 AUROC for DetectGPT. Eric Mitchell, Yoonho Lee 0001, Alexander Khazatsky, Christopher D. Manning, Chelsea Finn	ICML	5
2023	Train Offline, Test Online: A Real Robot Learning Benchmark abstract Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across labs), and we lack internet-scale robotics data. We take on these challenges via a new benchmark: Train Offline, Test Online (TOTO). TOTO provides remote users with access to shared robots for evaluating methods on common tasks and an open-source dataset of these tasks for offline training. Its manipulation task suite requires challenging generalization to unseen objects, positions, and lighting. We present initial results on TOTO comparing five pretrained visual representations and four offline policy learning baselines, remotely contributed by five institutions. The real promise of TOTO, however, lies in the future: we release the benchmark for additional submissions from any user, enabling easy, direct comparison to several methods without the need to obtain hardware or collect data. Gaoyue Zhou, Victoria Dean, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari, Kyle Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta 0001	ICRA	11
2023	Supervised Pretraining Can Learn In-Context Reinforcement Learning abstract Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trained to solve. In this paper, we study the in-context learning capabilities of transformers in decision-making problems, i.e., reinforcement learning (RL) for bandits and Markov decision processes. To do so, we introduce and study the Decision-Pretrained Transformer (DPT), a supervised pretraining method where a transformer predicts an optimal action given a query state and an in-context dataset of interactions from a diverse set of tasks. While simple, this procedure produces a model with several surprising capabilities. We find that the trained transformer can solve a range of RL problems in-context, exhibiting both exploration online and conservatism offline, despite not being explicitly trained to do so. The model also generalizes beyond the pretraining distribution to new tasks and automatically adapts its decision-making strategies to unknown structure. Theoretically, we show DPT can be viewed as an efficient implementation of Bayesian posterior sampling, a provably sample-efficient RL algorithm. We further leverage this connection to provide guarantees on the regret of the in-context algorithm yielded by DPT, and prove that it can learn faster than algorithms used to generate the pretraining data. These results suggest a promising yet simple path towards instilling strong in-context decision-making abilities in transformers. Jonathan Lee 0002, Annie Xie, Aldo Pacchiano, Yash Chandak, Chelsea Finn, Ofir Nachum, Emma Brunskill	NeurIPS	5
2023	Disentanglement via Latent Quantization abstract In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these sources, inductive biases take a paramount role in enabling disentanglement. In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. Concretely, we do this by (i) quantizing the latent space into discrete code vectors with a separate learnable scalar codebook per dimension and (ii) applying strong model regularization via an unusually high weight decay. Intuitively, the latent space design forces the encoder to combinatorially construct codes from a small number of distinct scalar values, which in turn enables the decoder to assign a consistent meaning to each value. Regularization then serves to drive the model towards this parsimonious strategy. We demonstrate the broad applicability of this approach by adding it to both basic data-reconstructing (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models. For reliable evaluation, we also propose InfoMEC, a new set of metrics for disentanglement that is cohesively grounded in information theory and fixes well-established shortcomings in previous metrics. Together with regularization, latent quantization dramatically improves the modularity and explicitness of learned representations on a representative suite of benchmark datasets. In particular, our quantized-latent autoencoder (QLAE) consistently outperforms strong methods from prior work in these key disentanglement properties without compromising data reconstruction. Kyle Hsu, William Dorrell, James C. R. Whittington, Jiajun Wu 0001, Chelsea Finn	NeurIPS	5
2023	Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning abstract A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave poorly during fine-tuning. In this paper, we devise an approach for learning an effective initialization from offline data that also enables fast online fine-tuning capabilities. Our approach, calibrated Q-learning (Cal-QL), accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale. We refer to this property as calibration, and define it formally as providing a lower bound on the true value function of the learned policy and an upper bound on the value of some other (suboptimal) reference policy, which may simply be the behavior policy. We show that offline RL algorithms that learn such calibrated value functions lead to effective online fine-tuning, enabling us to take the benefits of offline initializations in online fine-tuning. In practice, Cal-QL can be implemented on top of the conservative Q learning (CQL) for offline RL within a one-line code change. Empirically, Cal-QL outperforms state-of-the-art methods on 9/11 fine-tuning benchmark tasks that we study in this paper. Code and video are available at https://nakamotoo.github.io/Cal-QL Mitsuhiko Nakamoto, Simon Zhai, Anikait Singh, Max Sobol Mark, Yi Ma 0001, Chelsea Finn, Aviral Kumar, Sergey Levine	NeurIPS	6
2023	Direct Preference Optimization: Your Language Model is Secretly a Reward Model abstract While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing methods for gaining such steerability collect human labels of the relative quality of model generations and fine-tune the unsupervised LM to align with these preferences, often with reinforcement learning from human feedback (RLHF). However, RLHF is a complex and often unstable procedure, first fitting a reward model that reflects the human preferences, and then fine-tuning the large unsupervised LM using reinforcement learning to maximize this estimated reward without drifting too far from the original model. In this paper, we leverage a mapping between reward functions and optimal policies to show that this constrained reward maximization problem can be optimized exactly with a single stage of policy training, essentially solving a classification problem on the human preference data. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight, eliminating the need for fitting a reward model, sampling from the LM during fine-tuning, or performing significant hyperparameter tuning. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods. Notably, fine-tuning with DPO exceeds RLHF's ability to control sentiment of generations and improves response quality in summarization and single-turn dialogue while being substantially simpler to implement and train. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, Chelsea Finn	NeurIPS	6
2023	RoboCLIP: One Demonstration is Enough to Learn Robot Policies abstract Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL) methods attempt to circumvent these problems by utilizing expert demonstrations instead of using an extrinsic reward function but typically require a large number of in-domain expert demonstrations. Inspired by advances in the field of Video-and-Language Models (VLMs), we present RoboCLIP, an online imitation learning method that uses a single demonstration (overcoming the large data requirement) in the form of a video demonstration or a textual description of the task to generate rewards without manual reward function design. Additionally, RoboCLIP can also utilize out-of-domain demonstrations, like videos of humans solving the task for reward generation, circumventing the need to have the same demonstration and deployment domains. RoboCLIP utilizes pretrained VLMs without any finetuning for reward generation. Reinforcement learning agents trained with RoboCLIP rewards demonstrate 2-3 times higher zero-shot performance than competing imitation learning methods on downstream robot manipulation tasks, doing so using only one video/text demonstration. Visit our website at https://sites.google.com/view/roboclip/home for experiment videos. Sumedh A. Sontakke, Jesse Zhang, Sébastien M. R. Arnold, Karl Pertsch, Erdem Biyik, Dorsa Sadigh, Chelsea Finn, Laurent Itti	NeurIPS	7
2023	Permutation Equivariant Neural Functionals abstract This work studies the design of neural networks that can process the weights or gradients of other neural networks, which we refer to as neural functional networks (NFNs). Despite a wide range of potential applications, including learned optimization, processing implicit neural representations, network editing, and policy evaluation, there are few unifying principles for designing effective architectures that process the weights of other networks. We approach the design of neural functionals through the lens of symmetry, in particular by focusing on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. We introduce a framework for building permutation equivariant neural functionals, whose architectures encode these symmetries as an inductive bias. The key building blocks of this framework are NF-Layers (neural functional layers) that we constrain to be permutation equivariant through an appropriate parameter sharing scheme. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks that require processing the weights of MLPs and CNNs, such as predicting classifier generalization, producing "winning ticket" sparsity masks for initializations, and classifying or editing implicit neural representations (INRs). In addition, we provide code for our models and experiments at https://github.com/AllanYangZhou/nfn. Allan Zhou, Kaien Yang, Kaylee Burns, Adriano Cardace, Yiding Jiang, Samuel Sokota, J. Zico Kolter, Chelsea Finn	NeurIPS	8
2023	Neural Functional Transformers abstract The recent success of neural networks as implicit representation of data has driven growing interest in neural functionals: models that can process other neural networks as input by operating directly over their weight spaces. Nevertheless, constructing expressive and efficient neural functional architectures that can handle high-dimensional weight-space objects remains challenging. This paper uses the attention mechanism to define a novel set of permutation equivariant weight-space layers and composes them into deep equivariant models called neural functional Transformers (NFTs). NFTs respect weight-space permutation symmetries while incorporating the advantages of attention, which have exhibited remarkable success across multiple domains. In experiments processing the weights of feedforward MLPs and CNNs, we find that NFTs match or exceed the performance of prior weight-space methods. We also leverage NFTs to develop Inr2Array, a novel method for computing permutation invariant latent representations from the weights of implicit neural representations (INRs). Our proposed method improves INR classification accuracy by up to $+17\\%$ over existing methods. We provide an implementation of our layers at https://github.com/AllanYangZhou/nfn. Allan Zhou, Kaien Yang, Yiding Jiang, Kaylee Burns, Winnie Xu, Samuel Sokota, J. Zico Kolter, Chelsea Finn	NeurIPS	8
2022	Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference abstract Eric Mitchell, Joseph Noh, Siyan Li, Will Armstrong, Ananth Agarwal, Patrick Liu, Chelsea Finn, Christopher Manning. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022. Eric Mitchell, Joseph J. Noh, Siyan Li, William S. Armstrong, Ananth Agarwal, Patrick Liu, Chelsea Finn, Christopher D. Manning	EMNLP	7
2022	CoMPS: Continual Meta Policy Search Glen Berseth, Grace Zhang, Chelsea Finn, Sergey Levine	ICLR	4
2022	Vision-Based Manipulators Need to Also See from Their Hands Kyle Hsu, Moo Jin Kim, Rafael Rafailov, Jiajun Wu 0001, Chelsea Finn	ICLR	5
2022	Fast Model Editing at Scale Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, Christopher D. Manning	ICLR	4
2022	Extending the WILDS Benchmark for Unsupervised Adaptation Shiori Sagawa, Pang Wei Koh, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo 0002, Jure Leskovec, Kate Saenko, Tatsunori B. Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang	ICLR	19
2022	Autonomous Reinforcement Learning: Formalism and Benchmarking Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta 0004, Karol Hausman, Sergey Levine, Chelsea Finn	ICLR	7
2022	Meta-Learning with Fewer Tasks through Task Interpolation Huaxiu Yao, Linjun Zhang, Chelsea Finn	ICLR	3
2022	Do deep networks transfer invariances across classes? Allan Zhou, Fahim Tajwar, Alexander Robey, Tom Knowles, George J. Pappas, Seyed Hamed Hassani, Chelsea Finn	ICLR	7
2022	Memory-Based Model Editing at Scale abstract Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct undesirable behaviors. Existing model editors have shown promise, but also suffer from insufficient expressiveness: they struggle to accurately model an edit’s intended scope (examples affected by the edit), leading to inaccurate predictions for test inputs loosely related to the edit, and they often fail altogether after many edits. As a higher-capacity alternative, we propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC), which stores edits in an explicit memory and learns to reason over them to modulate the base model’s predictions as needed. To enable more rigorous evaluation of model editors, we introduce three challenging language model editing problems based on question answering, fact-checking, and dialogue generation. We find that only SERAC achieves high performance on all three problems, consistently outperforming existing approaches to model editing by a significant margin. Code, data, and additional project information will be made available at https://sites.google.com/view/serac-editing. Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning, Chelsea Finn	ICML	5
2022	A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning abstract While reinforcement learning (RL) provides a framework for learning through trial and error, translating RL algorithms into the real world has remained challenging. A major hurdle to real-world application arises from the development of algorithms in an episodic setting where the environment is reset after every trial, in contrast with the continual and non-episodic nature of the real-world encountered by embodied agents such as humans and robots. Enabling agents to learn behaviors autonomously in such non-episodic environments requires that the agent to be able to conduct its own trials. Prior works have considered an alternating approach where a forward policy learns to solve the task and the backward policy learns to reset the environment, but what initial state distribution should the backward policy reset the agent to? Assuming access to a few demonstrations, we propose a new method, MEDAL, that trains the backward policy to match the state distribution in the provided demonstrations. This keeps the agent close to the task-relevant states, allowing for a mix of easy and difficult starting states for the forward policy. Our experiments show that MEDAL matches or outperforms prior methods on three sparse-reward continuous control tasks from the EARL benchmark, with 40% gains on the hardest task, while making fewer assumptions than prior works. Archit Sharma, Rehaan Ahmad, Chelsea Finn	ICML	3
2022	Robust Policy Learning over Multiple Uncertainty Sets abstract Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast identification is not possible. Another dominant approach is robust RL which produces a policy that can handle worst-case scenarios, but these methods are generally designed to achieve robustness to a single uncertainty set that must be specified at train time. Towards a more general solution, we formulate the multi-set robustness problem to learn a policy robust to different perturbation sets. We then design an algorithm that enjoys the benefits of both system identification and robust RL: it reduces uncertainty where possible given a few interactions, but can still act robustly with respect to the remaining uncertainty. On a diverse set of control tasks, our approach demonstrates improved worst-case performance on new environments compared to prior methods based on system identification and on robust RL alone. Annie Xie, Shagun Sodhani, Chelsea Finn, Joelle Pineau, Amy Zhang 0001	ICML	3
2022	Improving Out-of-Distribution Robustness via Selective Augmentation abstract Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perform dramatically worse at test time. In this paper, we specifically consider the problems of subpopulation shifts (e.g., imbalanced data) and domain shifts. While prior works often seek to explicitly regularize internal representations or predictors of the model to be domain invariant, we instead aim to learn invariant predictors without restricting the model’s internal representations or predictors. This leads to a simple mixup-based technique which learns invariant predictors via selective augmentation called LISA. LISA selectively interpolates samples either with the same labels but different domains or with the same domain but different labels. Empirically, we study the effectiveness of LISA on nine benchmarks ranging from subpopulation shifts to domain shifts, and we find that LISA consistently outperforms other state-of-the-art methods and leads to more invariant predictors. We further analyze a linear setting and theoretically show how LISA leads to a smaller worst-group error. Huaxiu Yao, Yu Wang 0170, Sai Li 0005, Linjun Zhang, Weixin Liang, James Zou 0001, Chelsea Finn	ICML	7
2022	How to Leverage Unlabeled Data in Offline Reinforcement Learning abstract Offline reinforcement learning (RL) can learn control policies from static datasets but, like standard RL methods, it requires reward annotations for every transition. In many cases, labeling large datasets with rewards may be costly, especially if those rewards must be provided by human labelers, while collecting diverse unlabeled data might be comparatively inexpensive. How can we best leverage such unlabeled data in offline RL? One natural solution is to learn a reward function from the labeled data and use it to label the unlabeled data. In this paper, we find that, perhaps surprisingly, a much simpler method that simply applies zero rewards to unlabeled data leads to effective data sharing both in theory and in practice, without learning any reward model at all. While this approach might seem strange (and incorrect) at first, we provide extensive theoretical and empirical analysis that illustrates how it trades off reward bias, sample complexity and distributional shift, often leading to good results. We characterize conditions under which this simple strategy is effective, and further show that extending it with a simple reweighting approach can further alleviate the bias introduced by using incorrect reward labels. Our empirical evaluation confirms these findings in simulated robotic locomotion, navigation, and manipulation settings. Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine	ICML	5
2022	Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations abstract Spurious correlations pose a major challenge for robust machine learning. Models trained with empirical risk minimization (ERM) may learn to rely on correlations between class labels and spurious attributes, leading to poor performance on data groups without these correlations. This is challenging to address when the spurious attribute labels are unavailable. To improve worst-group performance on spuriously correlated data without training attribute labels, we propose Correct-N-Contrast (CNC), a contrastive approach to directly learn representations robust to spurious correlations. As ERM models can be good spurious attribute predictors, CNC works by (1) using a trained ERM model’s outputs to identify samples with the same class but dissimilar spurious features, and (2) training a robust model with contrastive learning to learn similar representations for these samples. To support CNC, we introduce new connections between worst-group error and a representation alignment loss that CNC aims to minimize. We empirically observe that worst-group error closely tracks with alignment loss, and prove that the alignment loss over a class helps upper-bound the class’s worst-group vs. average error gap. On popular benchmarks, CNC reduces alignment loss drastically, and achieves state-of-the-art worst-group accuracy by 3.6% average absolute lift. CNC is also competitive with oracle methods that require group labels. Nimit Sharad Sohoni, Hongyang R. Zhang, Chelsea Finn, Christopher Ré	ICML	4
2022	LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning abstract Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new samples. This setting is particularly well-suited for continuous control robotic applications for which online data collection based on trial-and-error is costly and potentially unsafe. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios, such as data from several human demonstrators or from policies that act with different purposes. Unfortunately, such datasets often contain action distributions with multiple modes and, in some cases, lack a sufficient number of high-reward trajectories, which render offline policy training inefficient. To address this challenge, we propose to leverage latent-variable generative model to represent high-advantage state-action pairs leading to better adherence to data distributions that contributes to solving the task, while maximizing reward via a policy over the latent variable. As we empirically show on a range of simulated locomotion, navigation, and manipulation tasks, our method referred to as latent-variable advantage-weighted policy optimization (LAPO), improves the average performance of the next best-performing offline reinforcement learning methods by 49\% on heterogeneous datasets, and by 8\% on datasets with narrow and biased distributions. Ali Ghadirzadeh, Tianhe Yu, Alex Yuan Gao, Liang Bin, Chelsea Finn, Chongjie Zhang	NeurIPS	8
2022	You Only Live Once: Single-Life Reinforcement Learning abstract Reinforcement learning algorithms are typically designed to learn a performant policy that can repeatedly and autonomously complete a task, usually starting from scratch. However, in many real-world situations, the goal might not be to learn a policy that can do the task repeatedly, but simply to perform a new task successfully once in a single trial. For example, imagine a disaster relief robot tasked with retrieving an item from a fallen building, where it cannot get direct supervision from humans. It must retrieve this object within one test-time trial, and must do so while tackling unknown obstacles, though it may leverage knowledge it has of the building before the disaster. We formalize this problem setting, which we call single-life reinforcement learning (SLRL), where an agent must complete a task within a single episode without interventions, utilizing its prior experience while contending with some form of novelty. SLRL provides a natural setting to study the challenge of autonomously adapting to unfamiliar situations, and we find that algorithms designed for standard episodic reinforcement learning often struggle to recover from out-of-distribution states in this setting. Motivated by this observation, we propose an algorithm, Q-weighted adversarial learning (QWALE), which employs a distribution matching strategy that leverages the agent's prior experience as guidance in novel situations. Our experiments on several single-life continuous control problems indicate that methods based on our distribution matching formulation are 20-60% more successful because they can more quickly recover from novel states. Annie S. Chen, Archit Sharma, Sergey Levine, Chelsea Finn	NeurIPS	4
2022	Learning Options via Compression abstract Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks.Skill learning offers one way of identifying these regularities by decomposing pre-collected experiences into a sequence of skills.A popular approach to skill learning is maximizing the likelihood of the pre-collected experience with latent variable models,where the latent variables represent the skills. However, there are often many solutions that maximize the likelihood equally well, including degenerate solutions. To address this underspecification, we propose a new objective that combines the maximum likelihood objective with a penalty on the description length of the skills. This penalty incentivizes the skills to maximally extract common structures from the experiences. Empirically, our objective learns skills that solve downstream tasks in fewer samples compared to skills learned from only maximizing likelihood. Further, while most prior works in the offline multi-task setting focus on tasks with low-dimensional observations, our objective can scale to challenging tasks with high-dimensional image observations. Yiding Jiang, Evan Zheran Liu, Benjamin Eysenbach, J. Zico Kolter, Chelsea Finn	NeurIPS	5
2022	Giving Feedback on Interactive Student Programs with Meta-Exploration abstract Developing interactive software, such as websites or games, is a particularly engaging way to learn computer science. However, teaching and giving feedback on such software is time-consuming — standard approaches require instructors to manually grade student-implemented interactive programs. As a result, online platforms that serve millions, like Code.org, are unable to provide any feedback on assignments for implementing interactive programs, which critically hinders students’ ability to learn. One approach toward automatic grading is to learn an agent that interacts with a student’s program and explores states indicative of errors via reinforcement learning. However, existing work on this approach only provides binary feedback of whether a program is correct or not, while students require finer-grained feedback on the specific errors in their programs to understand their mistakes. In this work, we show that exploring to discover errors can be cast as a meta-exploration problem. This enables us to construct a principled objective for discovering errors and an algorithm for optimizing this objective, which provides fine-grained feedback. We evaluate our approach on a set of over 700K real anonymized student programs from a Code.org interactive assignment. Our approach provides feedback with 94.3% accuracy, improving over existing approaches by 17.7% and coming within 1.5% of human-level accuracy. Project web page: https://ezliu.github.io/dreamgrader. Evan Zheran Liu, Moritz Stephan, Allen Nie, Chris Piech, Emma Brunskill, Chelsea Finn	NeurIPS	6
2022	When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning abstract A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which require external assistance to recover from, such as when a robot arm has pushed an object off of a table. While standard agents require constant monitoring to decide when to intervene, we aim to design proactive agents that can request human intervention only when needed. To this end, we propose an algorithm that efficiently learns to detect and avoid states that are irreversible, and proactively asks for help in case the agent does enter them. On a suite of continuous control environments with unknown irreversible states, we find that our algorithm exhibits better sample- and intervention-efficiency compared to existing methods. Annie Xie, Fahim Tajwar, Archit Sharma, Chelsea Finn	NeurIPS	4
2022	Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time abstract Distribution shifts occur when the test distribution differs from the training distribution, and can considerably degrade performance of machine learning models deployed in the real world. While recent works have studied robustness to distribution shifts, distribution shifts arising from the passage of time have the additional structure of timestamp metadata. Real-world examples of such shifts are underexplored, and it is unclear whether existing models can leverage trends in past distribution shifts to reliably extrapolate into the future. To address this gap, we curate Wild-Time, a benchmark of 5 datasets that reflect temporal distribution shifts arising in a variety of real-world applications, including drug discovery, patient prognosis, and news classification. On these datasets, we systematically benchmark 13 approaches with various inductive biases. We evaluate methods in domain-generalization, continual learning, self-supervised learning, and ensemble learning, which leverage timestamps to extract the common structure of the distribution shifts. We extend several domain-generalization methods to the temporal distribution shift setting by treating windows of time as different domains. Finally, we propose two evaluation strategies to evaluate model performance under temporal distribution shifts---evaluation with a fixed time split (Eval-Fix) and evaluation with a data stream (Eval-Stream). Eval-Fix, our primary evaluation strategy, aims to provide a simple evaluation protocol for the broader machine learning community, while Eval-Stream serves as a complementary benchmark for continual learning approaches. Our experiments demonstrate that existing methods are limited in tackling temporal distribution shift: across all settings, we observe an average performance drop of 20% from in-distribution to out-of-distribution data. Huaxiu Yao, Caroline Choi, Bochuan Cao, Yoonho Lee 0001, Pang Wei Koh, Chelsea Finn	NeurIPS	6
2022	C-Mixup: Improving Generalization in Regression abstract Improving the generalization of deep networks is an important open challenge, particularly in domains without plentiful data. The mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. These interpolated examples augment the original training set. Mixup has shown promising results in various classification tasks, but systematic analysis of mixup in regression remains underexplored. Using mixup directly on regression labels can result in arbitrarily incorrect labels. In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks. In contrast with vanilla mixup, which picks training examples for mixing with uniform probability, C-Mixup adjusts the sampling probability based on the similarity of the labels. Our theoretical analysis confirms that C-Mixup with label similarity obtains a smaller mean square error in supervised regression and meta-regression than vanilla mixup and using feature similarity. Another benefit of C-Mixup is that it can improve out-of-distribution robustness, where the test distribution is different from the training distribution. By selectively interpolating examples with similar labels, it mitigates the effects of domain-associated information and yields domain-invariant representations. We evaluate C-Mixup on eleven datasets, ranging from tabular to video data. Compared to the best prior approach, C-Mixup achieves 6.56%, 4.76%, 5.82% improvements in in-distribution generalization, task generalization, and out-of-distribution robustness, respectively. Code is released at https://github.com/huaxiuyao/C-Mixup. Huaxiu Yao, Yiping Wang 0003, Linjun Zhang, James Zou 0001, Chelsea Finn	NeurIPS	5
2022	MEMO: Test Time Robustness via Adaptation and Augmentation abstract While deep neural networks can attain good accuracy on in-distribution test points, many applications require robustness even in the face of unexpected perturbations in the input, changes in the domain, or other sources of distribution shift. We study the problem of test time robustification, i.e., using the test input to improve model robustness. Recent prior works have proposed methods for test time adaptation, however, they each introduce additional assumptions, such as access to multiple test points, that prevent widespread adoption. In this work, we aim to study and devise methods that make no assumptions about the model training process and are broadly applicable at test time. We propose a simple approach that can be used in any test setting where the model is probabilistic and adaptable: when presented with a test example, perform different data augmentations on the data point, and then adapt (all of) the model parameters by minimizing the entropy of the model's average, or marginal, output distribution across the augmentations. Intuitively, this objective encourages the model to make the same prediction across different augmentations, thus enforcing the invariances encoded in these augmentations, while also maintaining confidence in its predictions. In our experiments, we evaluate two baseline ResNet models, two robust ResNet-50 models, and a robust vision transformer model, and we demonstrate that this approach achieves accuracy gains of 1-8% over standard model evaluation and also generally outperforms prior augmentation and adaptation strategies. For the setting in which only one test point is available, we achieve state-of-the-art results on the ImageNet-C, ImageNet-R, and, among ResNet-50 models, ImageNet-A distribution shift benchmarks. Marvin Zhang, Sergey Levine, Chelsea Finn	NeurIPS	3
2022	Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models abstract We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by introducing an action latent variable such that the feed-forward policy search can be divided into two parts: (i) training a sub-policy that outputs a distribution over the action latent variable given a state of the system, and (ii) unsupervised training of a generative model that outputs a sequence of motor actions conditioned on the latent action variable. GenRL enables safe exploration and alleviates the data-inefficiency problem as it exploits prior knowledge about valid sequences of motor actions. Moreover, we provide a set of measures for evaluation of generative models such that we are able to predict the performance of the RL policy training prior to the actual training on a physical robot. We experimentally determine the characteristics of generative models that have most influence on the performance of the final policy training on two robotics tasks: shooting a hockey puck and throwing a basketball. Furthermore, we empirically demonstrate that GenRL is the only method which can safely and efficiently solve the robotics tasks compared to two state-of-the-art RL methods. Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman	J. Mach. Learn. Res.	4
2021	Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction abstract A video prediction model that generalizes to diverse scenes would enable intelligent agents such as robots to perform a variety of tasks via planning with the model. However, while existing video prediction models have produced promising results on small datasets, they suffer from severe underfitting when trained on large and diverse datasets. To address this underfitting challenge, we first observe that the ability to train larger video prediction models is often bottlenecked by the memory constraints of GPUs or TPUs. In parallel, deep hierarchical latent variable models can produce higher quality predictions by capturing the multi-level stochasticity of future observations, but end-to-end optimization of such models is notably difficult. Our key insight is that greedy and modular optimization of hierarchical autoencoders can simultaneously address both the memory constraints and the optimization challenges of large-scale video prediction. We introduce Greedy Hierarchical Variational Autoencoders (GHVAEs), a method that learns highfidelity video predictions by greedily training each level of a hierarchical autoencoder. In comparison to state- of-the-art models, GHVAEs provide 17-55% gains in prediction performance on four video datasets, a 35–40% higher success rate on real robot tasks, and can improve performance monotonically by simply adding more modules. Visualization and more details are at https://sites.google.com/view/ghvae. Bohan Wu, Suraj Nair 0003, Roberto Martin Martin, Li Fei-Fei 0001, Chelsea Finn	CVPR	5
2021	SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments Glen Berseth, Daniel Geng, Coline Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine	ICLR	5
2021	Model-Based Visual Planning with Self-Supervised Functional Distances Stephen Tian, Suraj Nair 0003, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine	ICLR	6
2021	Meta-learning Symmetries by Reparameterization Allan Zhou, Tom Knowles, Chelsea Finn	ICLR	3
2021	Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills abstract We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data. In particular, we propose the objective of learning a functional understanding of the environment by learning to reach any goal state in a given dataset. We employ goal-conditioned Q-learning with hindsight relabeling and develop several techniques that enable training in a particularly challenging offline setting. We find that our method can operate on high-dimensional camera images and learn a variety of skills on real robots that generalize to previously unseen scenes and objects. We also show that our method can learn to reach long-horizon goals across multiple episodes through goal chaining, and learn rich representations that can help with downstream tasks through pre-training or auxiliary objectives. Yevgen Chebotar, Karol Hausman, Yao Lu 0006, Ted Xiao, Dmitry Kalashnikov, Jacob Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, Sergey Levine	ICML	10
2021	Catformer: Designing Stable Transformers via Sensitivity Analysis abstract Transformer architectures are widely used, but training them is non-trivial, requiring custom learning rate schedules, scaling terms, residual connections, careful placement of submodules such as normalization, and so on. In this paper, we improve upon recent analysis of Transformers and formalize a notion of sensitivity to capture the difficulty of training. Sensitivity characterizes how the variance of activation and gradient norms change in expectation when parameters are randomly perturbed. We analyze the sensitivity of previous Transformer architectures and design a new architecture, the Catformer, which replaces residual connections or RNN-based gating mechanisms with concatenation. We prove that Catformers are less sensitive than other Transformer variants and demonstrate that this leads to more stable training. On DMLab30, a suite of high-dimension reinforcement tasks, Catformer outperforms other transformers, including Gated Transformer-XL—the state-of-the-art architecture designed to address stability—by 13%. Jared Davis, Albert Gu, Krzysztof Choromanski, Tri Dao, Christopher Ré, Chelsea Finn, Percy Liang	ICML	6
2021	WILDS: A Benchmark of in-the-Wild Distribution Shifts abstract Distribution shifts—where the training distribution differs from the test distribution—can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments, these distribution shifts are under-represented in the datasets widely used in the ML community today. To address this gap, we present WILDS, a curated benchmark of 10 datasets reflecting a diverse range of distribution shifts that naturally arise in real-world applications, such as shifts across hospitals for tumor identification; across camera traps for wildlife monitoring; and across time and location in satellite imaging and poverty mapping. On each dataset, we show that standard training yields substantially lower out-of-distribution than in-distribution performance. This gap remains even with models trained by existing methods for tackling distribution shifts, underscoring the need for new methods for training models that are more robust to the types of distribution shifts that arise in practice. To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations. The full paper, code, and leaderboards are available at https://wilds.stanford.edu. Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard L. Phillips, Irena Gao, Etienne David, Ian Stavness, Wei Guo 0002, Berton Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang	ICML	22
2021	Just Train Twice: Improving Group Robustness without Training Group Information abstract Standard training via empirical risk minimization (ERM) can produce models that achieve low error on average but high error on minority groups, especially in the presence of spurious correlations between the input and label. Prior approaches to this problem, like group distributionally robust optimization (group DRO), generally require group annotations for every training point. On the other hand, approaches that do not use group annotations generally do not improve minority performance. For example, we find that joint DRO, which dynamically upweights examples with high training loss, tends to optimize for examples that are irrelevant to the specific groups we seek to do well on. In this paper, we propose a simple two-stage approach, JTT, that achieves comparable performance to group DRO while only requiring group annotations on a significantly smaller validation set. JTT first attempts to identify informative training examples, which are often minority examples, by training an initial ERM classifier and selecting the examples with high training loss. Then, it trains a final classifier by upsampling the selected examples. Crucially, unlike joint DRO, JTT does not iteratively upsample examples that have high loss under the final classifier. On four image classification and natural language processing tasks with spurious correlations, we show that JTT closes 85% of the gap in accuracy on the worst group between ERM and group DRO. Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, Chelsea Finn	ICML	8
2021	Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices abstract The goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and exploiting this information to solve the task. In principle, optimal exploration and exploitation can be learned end-to-end by simply maximizing task performance. However, such meta-RL approaches struggle with local optima due to a chicken-and-egg problem: learning to explore requires good exploitation to gauge the exploration’s utility, but learning to exploit requires information gathered via exploration. Optimizing separate objectives for exploration and exploitation can avoid this problem, but prior meta-RL exploration objectives yield suboptimal policies that gather information irrelevant to the task. We alleviate both concerns by constructing an exploitation objective that automatically identifies task-relevant information and an exploration objective to recover only this information. This avoids local optima in end-to-end training, without sacrificing optimal exploration. Empirically, DREAM substantially outperforms existing approaches on complex meta-RL problems, such as sparse-reward 3D visual navigation. Videos of DREAM: https://ezliu.github.io/dream/ Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn	ICML	4
2021	Offline Meta-Reinforcement Learning with Advantage Weighting abstract This paper introduces the offline meta-reinforcement learning (offline meta-RL) problem setting and proposes an algorithm that performs well in this setting. Offline meta-RL is analogous to the widely successful supervised learning strategy of pre-training a model on a large batch of fixed, pre-collected data (possibly from various tasks) and fine-tuning the model to a new task with relatively little data. That is, in offline meta-RL, we meta-train on fixed, pre-collected data from several tasks and adapt to a new task with a very small amount (less than 5 trajectories) of data from the new task. By nature of being offline, algorithms for offline meta-RL can utilize the largest possible pool of training data available and eliminate potentially unsafe or costly data collection during meta-training. This setting inherits the challenges of offline RL, but it differs significantly because offline RL does not generally consider a) transfer to new tasks or b) limited data from the test task, both of which we face in offline meta-RL. Targeting the offline meta-RL setting, we propose Meta-Actor Critic with Advantage Weighting (MACAW). MACAW is an optimization-based meta-learning algorithm that uses simple, supervised regression objectives for both the inner and outer loop of meta-training. On offline variants of common meta-RL benchmarks, we empirically find that this approach enables fully offline meta-reinforcement learning and achieves notable gains over prior methods. Eric Mitchell, Rafael Rafailov, Xue Bin Peng, Sergey Levine, Chelsea Finn	ICML	5
2021	Deep Reinforcement Learning amidst Continual Structured Non-Stationarity abstract As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms that replay past experiences when learning. In this work, we formalize this problem setting, and draw upon ideas from the online learning and probabilistic inference literature to derive an off-policy RL algorithm that can reason about and tackle such lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences, and performs off-policy RL with this representation. We further introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift. Annie Xie, James Harrison, Chelsea Finn	ICML	3
2021	Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms abstract Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem. Ali Ghadirzadeh, Xi Chen 0051, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic	IROS	4
2021	Noether Networks: meta-learning useful conserved quantities abstract Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-learning useful conserved quantities. We propose Noether Networks: a new type of architecture where a meta-learned conservation loss is optimized inside the prediction function. We show, theoretically and experimentally, that Noether Networks improve prediction quality, providing a general framework for discovering inductive biases in sequential problems. Ferran Alet, Dylan Doblar, Allan Zhou, Josh Tenenbaum, Kenji Kawaguchi, Chelsea Finn	NeurIPS	6
2021	Efficiently Identifying Task Groupings for Multi-Task Learning abstract Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive. As a result, efficiently identifying the tasks that would benefit from training together remains a challenging design question without a clear solution. In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task groupings in a single run by training all tasks together and quantifying the effect to which one task's gradient would affect another task's loss. On the large-scale Taskonomy computer vision dataset, we find this method can decrease test loss by 10.0% compared to simply training all tasks together while operating 11.6 times faster than a state-of-the-art task grouping method. Christopher Fifty, Ehsan Amid, Zhe Zhao 0001, Tianhe Yu, Rohan Anil, Chelsea Finn	NeurIPS	6
2021	Visual Adversarial Imitation Learning using Variational Models abstract Reward function specification, which requires considerable human effort and iteration, remains a major impediment for learning behaviors through deep reinforcement learning. In contrast, providing visual demonstrations of desired behaviors presents an easier and more natural way to teach agents. We consider a setting where an agent is provided a fixed dataset of visual demonstrations illustrating how to perform a task, and must learn to solve the task using the provided demonstrations and unsupervised environment interactions. This setting presents a number of challenges including representation learning for visual observations, sample complexity due to high dimensional spaces, and learning instability due to the lack of a fixed reward or learning signal. Towards addressing these challenges, we develop a variational model-based adversarial imitation learning (V-MAIL) algorithm. The model-based approach provides a strong signal for representation learning, enables sample efficiency, and improves the stability of adversarial training by enabling on-policy learning. Through experiments involving several vision-based locomotion and manipulation tasks, we find that V-MAIL learns successful visuomotor policies in a sample-efficient manner, has better stability compared to prior work, and also achieves higher asymptotic performance. We further find that by transferring the learned models, V-MAIL can learn new tasks from visual demonstrations without any additional environment interactions. All results including videos can be found online at https://sites.google.com/view/variational-mail Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn	NeurIPS	4
2021	Information is Power: Intrinsic Control via Information Capture abstract Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in artificial agents is concerned with the following question: what is a good general-purpose objective for an agent? We study this question in dynamic partially-observed environments, and argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states. We instantiate this approach as a deep reinforcement learning agent equipped with a deep variational Bayes filter. We find that our agent learns to discover, represent, and exercise control of dynamic objects in a variety of partially-observed environments sensed with visual observations without extrinsic reward. Nicholas Rhinehart, Jenny Wang, Glen Berseth, John D. Co-Reyes, Danijar Hafner, Chelsea Finn, Sergey Levine	NeurIPS	6
2021	Autonomous Reinforcement Learning via Subgoal Curricula abstract Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each trial needs to start from a fixed initial state distribution. Unfortunately, resetting the environment to its initial state after each trial requires substantial amount of human supervision and extensive instrumentation of the environment which defeats the goal of autonomous acquisition of complex behaviors. In this work, we propose Value-accelerated Persistent Reinforcement Learning (VaPRL), which generates a curriculum of initial states such that the agent can bootstrap on the success of easier tasks to efficiently learn harder tasks. The agent also learns to reach the initial states proposed by the curriculum, minimizing the reliance on human interventions into the learning. We observe that VaPRL reduces the interventions required by three orders of magnitude compared to episodic RL while outperforming prior state-of-the art methods for reset-free RL both in terms of sample efficiency and asymptotic performance on a variety of simulated robotics problems. Archit Sharma, Abhishek Gupta 0004, Sergey Levine, Karol Hausman, Chelsea Finn	NeurIPS	5
2021	Meta-learning with an Adaptive Task Scheduler abstract To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability, under the assumption that tasks are of equal importance. However, it is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks. To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS) for the meta-training process. In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks. We identify two meta-model-related factors as the input of the neural scheduler, which characterize the difficulty of a candidate task to the meta-model. Theoretically, we show that a scheduler taking the two factors into account improves the meta-training loss and also the optimization landscape. Under the setting of meta-learning with noise and limited budgets, ATS improves the performance on both miniImageNet and a real-world drug discovery benchmark by up to 13% and 18%, respectively, compared to state-of-the-art task schedulers. Huaxiu Yao, Yu Wang 0170, Ying Wei 0001, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn	NeurIPS	7
2021	Conservative Data Sharing for Multi-Task Offline Reinforcement Learning abstract Offline reinforcement learning (RL) algorithms have shown promising results in domains where abundant pre-collected data is available. However, prior methods focus on solving individual problems from scratch with an offline dataset without considering how an offline RL agent can acquire multiple skills. We argue that a natural use case of offline RL is in settings where we can pool large amounts of data collected in various scenarios for solving different tasks, and utilize all of this data to learn behaviors for all the tasks more effectively rather than training each one in isolation. However, sharing data across all tasks in multi-task offline RL performs surprisingly poorly in practice. Thorough empirical analysis, we find that sharing data can actually exacerbate the distributional shift between the learned policy and the dataset, which in turn can lead to divergence of the learned policy and poor performance. To address this challenge, we develop a simple technique for data- sharing in multi-task offline RL that routes data based on the improvement over the task-specific data. We call this approach conservative data sharing (CDS), and it can be applied with multiple single-task offline RL methods. On a range of challenging multi-task locomotion, navigation, and vision-based robotic manipulation problems, CDS achieves the best or comparable performance compared to prior offline multi- task RL methods and previous data sharing approaches. Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn	NeurIPS	6
2021	COMBO: Conservative Offline Model-Based Policy Optimization abstract Model-based reinforcement learning (RL) algorithms, which learn a dynamics model from logged experience and perform conservative planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL). However, practical variants of such model-based algorithms rely on explicit uncertainty quantification for incorporating conservatism. Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We empirically find that uncertainty estimation is not accurate and leads to poor performance in certain scenarios in offline model-based RL. We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that trains a value function using both the offline dataset and data generated using rollouts under the model while also additionally regularizing the value function on out-of-support state-action tuples generated via model rollouts. This results in a conservative estimate of the value function for out-of-support state-action tuples, without requiring explicit uncertainty estimation. Theoretically, we show that COMBO satisfies a policy improvement guarantee in the offline setting. Through extensive experiments, we find that COMBO attains greater performance compared to prior offline RL on problems that demand generalization to related but previously unseen tasks, and also consistently matches or outperforms prior offline RL methods on widely studied offline RL benchmarks, including image-based tasks. Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn	NeurIPS	6
2021	Differentiable Annealed Importance Sampling and the Perils of Gradient Noise abstract Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation, but are not fully differentiable due to the use of Metropolis-Hastings correction steps. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective using gradient-based methods. To this end, we propose Differentiable AIS (DAIS), a variant of AIS which ensures differentiability by abandoning the Metropolis-Hastings corrections. As a further advantage, DAIS allows for mini-batch gradients. We provide a detailed convergence analysis for Bayesian linear regression which goes beyond previous analyses by explicitly accounting for the sampler not having reached equilibrium. Using this analysis, we prove that DAIS is consistent in the full-batch setting and provide a sublinear convergence rate. Furthermore, motivated by the problem of learning from large-scale datasets, we study a stochastic variant of DAIS that uses mini-batch gradients. Surprisingly, stochastic DAIS can be arbitrarily bad due to a fundamental incompatibility between the goals of last-iterate convergence to the posterior and elimination of the accumulated stochastic error. This is in stark contrast with other settings such as gradient-based optimization and Langevin dynamics, where the effect of gradient noise can be washed out by taking smaller steps. This indicates that annealing-based marginal likelihood estimation with stochastic gradients may require new ideas. Guodong Zhang 0006, Kyle Hsu, Chelsea Finn, Roger B. Grosse	NeurIPS	4
2021	Adaptive Risk Minimization: Learning to Adapt to Domain Shift abstract A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning systems are regularly tested under distribution shift, due to changing temporal correlations, atypical end users, or other factors. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts, corresponding to new domains or domain distributions. Most prior methods aim to learn a single robust model or invariant feature space that performs well on all domains. In contrast, we aim to learn models that adapt at test time to domain shift using unlabeled test points. Our primary contribution is to introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains. Compared to prior methods for robustness, invariance, and adaptation, ARM methods provide performance gains of 1-4% test accuracy on a number of image classification problems exhibiting domain shift. Marvin Zhang, Henrik Marklund, Nikita Dhawan, Abhishek Gupta 0004, Sergey Levine, Chelsea Finn	NeurIPS	6
2020	Learning to Interactively Learn and Assist abstract When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format of information exchanged between the human and the agent. While scalar rewards carry little information, demonstrations require significant effort to provide and may carry more information than is necessary. Furthermore, rewards and demonstrations are often defined and collected before training begins, when the human is most uncertain about what information would help the agent. In contrast, when humans communicate objectives with each other, they make use of a large vocabulary of informative behaviors, including non-verbal communication, and often communicate throughout learning, responding to observed behavior. In this way, humans communicate intent with minimal effort. In this paper, we propose such interactive learning as an alternative to reward or demonstration-driven learning. To accomplish this, we introduce a multi-agent training framework that enables an agent to learn from another agent who knows the current task. Through a series of experiments, we demonstrate the emergence of a variety of interactive learning behaviors, including information-sharing, information-seeking, and question-answering. Most importantly, we find that our approach produces an agent that is capable of learning interactively from a human user, without a set of explicit demonstrations or a reward function, and achieving significantly better performance cooperatively with a human than a human performing the task alone. Mark Woodward, Chelsea Finn, Karol Hausman	AAAI	2
2020	Learning Predictive Models from Observation and Interaction Karl Schmeckpeper, Annie Xie, Oleh Rybkin, Stephen Tian, Kostas Daniilidis, Sergey Levine, Chelsea Finn	ECCV (20)	7
2020	Model Based Reinforcement Learning for Atari Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski	ICLR	8
2020	VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation Manoj Kumar 0019, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma	ICLR	4
2020	Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation Suraj Nair 0003, Chelsea Finn	ICLR	2
2020	Meta-Learning without Memorization Mingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, Chelsea Finn	ICLR	5
2020	Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards Allan Zhou, Eric Jang, Daniel Kappler, Mohi Khansari, Paul Wohlhart, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn	ICLR	10
2020	On the Expressivity of Neural Networks for Deep Reinforcement Learning abstract We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, Q-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal Q-functions and policies are much more complex than the dynamics. For these MDPs, model-based planning is a favorable algorithm, because the resulting policies can approximate the optimal policy significantly better than a neural network parameterization can, and model-free or model-based policy optimization rely on policy parameterization. Motivated by the theory, we apply a simple multi-step model-based bootstrapping planner (BOOTS) to bootstrap a weak Q-function into a stronger policy. Empirical results show that applying BOOTS on top of model-based or model-free policy optimization algorithms at the test time improves the performance on benchmark tasks. Kefan Dong, Yuping Luo, Tianhe Yu, Chelsea Finn, Tengyu Ma 0001	ICML	4
2020	Goal-Aware Prediction: Learning to Model What Matters abstract Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model (future state reconstruction), and that of the downstream planner or policy (completing a specified task). This issue is exacerbated by vision-based control tasks in diverse real-world environments, where the complexity of the real world dwarfs model capacity. In this paper, we propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space, resulting in a learning objective that more closely matches the downstream task. Further, we do so in an entirely self-supervised manner, without the need for a reward function or image labels. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning. Suraj Nair 0003, Silvio Savarese, Chelsea Finn	ICML	3
2020	Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings abstract Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation" task setting: an agent first trains in non-safety-critical "source" environments such as in a simulator, before it adapts to the target environment where failures carry heavy costs. We propose a solution approach, CARL, that builds on the intuition that prior experience in diverse environments equips an agent to estimate risk, which in turn enables relative safety through risk-averse, cautious adaptation. CARL first employs model-based RL to train a probabilistic model to capture uncertainty about transition dynamics and catastrophic states across varied source environments. Then, when exploring a new safety-critical environment with unknown dynamics, the CARL agent plans to avoid actions that could lead to catastrophic states. In experiments on car driving, cartpole balancing, and half-cheetah locomotion, CARL successfully acquires cautious exploration behaviors, yielding higher rewards with fewer failures than strong RL adaptation baselines. Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman	ICML	3
2020	TRASS: Time Reversal as Self-Supervision abstract A longstanding challenge in robot learning for manipulation tasks has been the ability to generalize to varying initial conditions, diverse objects, and changing objectives. Learning based approaches have shown promise in producing robust policies, but require heavy supervision and large number of environment interactions, especially from visual inputs. We propose a novel self-supervision technique that uses time-reversal to provide high level supervision to reach goals. In particular, we introduce the time-reversal model (TRM), a self-supervised model which explores outward from a set of goal states and learns to predict these trajectories in reverse. This provides a high level plan towards goals, allowing us to learn complex manipulation tasks with no demonstrations or exploration at test time. We test our method on the domain of assembly, specifically the mating of tetris-style block pairs. Using our method operating atop visual model predictive control, we are able to assemble tetris blocks on a KuKa IIWA-7 using only uncalibrated RGB camera input, and generalize to unseen block pairs. Project's-page: https://sites.google.com/view/time-reversal. Suraj Nair 0003, Mohammad Babaeizadeh, Chelsea Finn, Sergey Levine	ICRA	3
2020	OmniTact: A Multi-Directional High-Resolution Touch Sensor abstract Incorporating touch as a sensing modality for robots can enable finer and more robust manipulation skills. Existing tactile sensors are either flat, have small sensitive fields or only provide low-resolution signals. In this paper, we introduce OmniTact, a multi-directional high-resolution tactile sensor. OmniTact is designed to be used as a fingertip for robotic manipulation with robotic hands, and uses multiple micro-cameras to detect multi-directional deformations of a gel-based skin. This provides a rich signal from which a variety of different contact state variables can be inferred using modern image processing and computer vision methods. We evaluate the capabilities of OmniTact on a challenging robotic control task that requires inserting an electrical connector into an outlet, as well as a state estimation problem that is representative of those typically encountered in dexterous robotic manipulation, where the goal is to infer the angle of contact of a curved finger pressing against an object. Both tasks are performed using only touch sensing and deep convolutional neural networks to process images from the sensor's cameras. We compare with a state-of-the-art tactile sensor that is only sensitive on one side, as well as a state-of-the-art multi-directional tactile sensor, and find that OmniTact's combination of high-resolution and multi-directional sensing is crucial for reliably inserting the electrical connector and allows for higher accuracy in the state estimation task. Videos and supplementary material can be found here4. Akhil Padmanabha, Frederik Ebert, Stephen Tian, Roberto Calandra, Chelsea Finn, Sergey Levine	ICRA	5
2020	Scalable Multi-Task Imitation Learning with Autonomous Improvement abstract While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively generalize broadly. Imitation learning, in particular, has remained a stable and powerful approach for robot learning, but critically relies on expert operators for data collection. In this work, we target this challenge, aiming to build an imitation learning system that can continuously improve through autonomous data collection, while simultaneously avoiding the explicit use of reinforcement learning, to maintain the stability, simplicity, and scalability of supervised imitation. To accomplish this, we cast the problem of imitation with autonomous improvement into a multi-task setting. We utilize the insight that, in a multi-task setting, a failed attempt at one task might represent a successful attempt at another task. This allows us to leverage the robot's own trials as demonstrations for tasks other than the one that the robot actually attempted. Using an initial dataset of multitask demonstration data, the robot autonomously collects trials which are only sparsely labeled with a binary indication of whether the trial accomplished any useful task or not. We then embed the trials into a learned latent space of tasks, trained using only the initial demonstration dataset, to draw similarities between various trials, enabling the robot to achieve one-shot generalization to new tasks. In contrast to prior imitation learning approaches, our method can autonomously collect data with sparse supervision for continuous improvement, and in contrast to reinforcement learning algorithms, our method can effectively improve from sparse, task-agnostic reward signals. Avi Singh, Eric Jang, Alex Irpan, Daniel Kappler, Murtaza Dalal, Sergey Levine, Mohi Khansari, Chelsea Finn	ICRA	8
2020	Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning abstract Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. In contrast to gradient-based meta-learning algorithms that rely on second-order gradient estimation, we introduce a more noise-tolerant Batch Hill-Climbing adaptation operator and combine it with meta-learning based on evolutionary strategies. Our method significantly improves adaptation to changes in dynamics in high noise settings, which are common in robotics applications. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics. We observe that our method significantly outperforms prior gradient-based approaches, enabling the robot to adapt its policy to changes based on less than 3 minutes of real data. Xingyou Song, Yuxiang Yang 0007, Krzysztof Choromanski, Ken Caluwaerts, Chelsea Finn, Jie Tan 0001	IROS	6
2020	Continuous Meta-Learning without Tasks abstract Meta-learning is a promising strategy for learning to efficiently learn using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task, and at test-time, the algorithms are optimized to learn in a single task. In this work, we enable the application of generic meta-learning algorithms to settings where this task segmentation is unavailable, such as continual online learning with unsegmented time series data. We present meta-learning via online changepoint analysis (MOCA), an approach which augments a meta-learning algorithm with a differentiable Bayesian changepoint detection scheme. The framework allows both training and testing directly on time series data without segmenting it into discrete tasks. We demonstrate the utility of this approach on three nonlinear meta-regression benchmarks as well as two meta-image-classification benchmarks. James Harrison, Apoorva Sharma, Chelsea Finn, Marco Pavone 0001	NeurIPS	3
2020	One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL abstract While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specified variation in the training task or environment. However, this may be infeasible in practical situations, either because making perturbations is not possible, or because it is unclear how to choose suitable perturbation strategies without sacrificing performance. The key insight of this work is that learning diverse behaviors for accomplishing a task can directly lead to behavior that generalizes to varying environments, without needing to perform explicit perturbations during training. By identifying multiple solutions for the task in a single environment during training, our approach can generalize to new situations by abandoning solutions that are no longer effective and adopting those that are. We theoretically characterize a robustness set of environments that arises from our algorithm and empirically find that our diversity-driven approach can extrapolate to various changes in the environment and task. Saurabh Kumar 0004, Aviral Kumar, Sergey Levine, Chelsea Finn	NeurIPS	4
2020	Weakly-Supervised Reinforcement Learning for Controllable Behavior abstract Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient exploration and provides a representation that captures distance between states. On a variety of challenging, vision-based continuous control problems, our approach leads to substantial performance gains, particularly as the complexity of the environment grows. Lisa Lee, Benjamin Eysenbach, Ruslan Salakhutdinov, Shixiang Gu, Chelsea Finn	NeurIPS	5
2020	Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors abstract The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and then gradually filling in details. In contrast, current learning approaches for visual prediction and planning fail on long-horizon tasks as they generate predictions (1)~without considering goal information, and (2)~at the finest temporal resolution, one step at a time. In this work we propose a framework for visual prediction and planning that is able to overcome both of these limitations. First, we formulate the problem of predicting towards a goal and propose the corresponding class of latent space goal-conditioned predictors (GCPs). GCPs significantly improve planning efficiency by constraining the search space to only those trajectories that reach the goal. Further, we show how GCPs can be naturally formulated as hierarchical models that, given two observations, predict an observation between them, and by recursively subdividing each part of the trajectory generate complete sequences. This divide-and-conquer strategy is effective at long-term prediction, and enables us to design an effective hierarchical planning algorithm that optimizes trajectories in a coarse-to-fine manner. We show that by using both goal-conditioning and hierarchical prediction, GCPs enable us to solve visual planning tasks with much longer horizon than previously possible. See prediction and planning videos on the supplementary website: sites.google.com/view/video-gcp. Karl Pertsch, Oleh Rybkin, Frederik Ebert, Shenghao Zhou, Dinesh Jayaraman, Chelsea Finn, Sergey Levine	NeurIPS	6
2020	Continual Learning of Control Primitives : Skill Discovery via Reset-Games abstract Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when an agent attempts a tasks and fails, the environment must somehow "reset" so that the agent can attempt the task again. While easy in simulation, this could require considerable human effort in the real world, especially if the number of trials is very large. Second, real world learning is often limited by challenges in exploration, as complex, temporally extended behavior is often times difficult to acquire with random exploration. In this work, we show how a single method can allow an agent to acquire skills with minimal supervision while removing the need for resets. We do this by exploiting the insight that the need to reset" an agent to a broad set of initial states for a learning task provides a natural setting to learn a diverse set ofreset-skills." We propose a general-sum game formulation that naturally balances the objective of resetting and learning skills, and demonstrate that this approach improves performance on reset-free tasks, and additionally show that the skills we obtain can be used to significantly accelerate downstream learning. Kelvin Xu, Siddharth Verma, Chelsea Finn, Sergey Levine	NeurIPS	3
2020	Gradient Surgery for Multi-Task Learning abstract While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks to enable more efficient learning. However, the multi-task setting presents a number of optimization challenges, making it difficult to realize large efficiency gains compared to learning tasks independently. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a gradient. On a series of challenging multi-task supervised and multi-task RL problems, this approach leads to substantial gains in efficiency and performance. Further, it is model-agnostic and can be combined with previously-proposed multi-task architectures for enhanced performance. Tianhe Yu, Saurabh Kumar 0004, Abhishek Gupta 0004, Sergey Levine, Karol Hausman, Chelsea Finn	NeurIPS	6
2020	MOPO: Model-based Offline Policy Optimization abstract Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a batch of previously collected data. This problem setting is compelling, because it offers the promise of utilizing large, diverse, previously collected datasets to acquire policies without any costly or dangerous active exploration, but it is also exceptionally difficult, due to the distributional shift between the offline training data and the learned policy. While there has been significant progress in model-free offline RL, the most successful prior methods constrain the policy to the support of the data, precluding generalization to new states. In this paper, we observe that an existing model-based RL algorithm on its own already produces significant gains in the offline setting, as compared to model-free approaches, despite not being designed for this setting. However, although many standard model-based RL methods already estimate the uncertainty of their model, they do not by themselves provide a mechanism to avoid the issues associated with distributional shift in the offline setting. We therefore propose to modify existing model-based RL methods to address these issues by casting offline model-based RL into a penalized MDP framework. We theoretically show that, by using this penalized MDP, we are maximizing a lower bound of the return in the true MDP. Based on our theoretical results, we propose a new model-based offline RL algorithm that applies the variance of a Lipschitz-regularized model as a penalty to the reward function. We find that this algorithm outperforms both standard model-based RL methods and existing state-of-the-art model-free offline RL approaches on existing offline RL benchmarks, as well as two challenging continuous control tasks that require generalizing from data collected for a different task. Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou 0001, Sergey Levine, Chelsea Finn, Tengyu Ma 0001	NeurIPS	7
2019	Unsupervised Learning via Meta-Learning Kyle Hsu, Sergey Levine, Chelsea Finn	ICLR (Poster)	3
2019	Reasoning About Physical Interactions with Object-Oriented Prediction and Planning Michael Janner, Sergey Levine, William T. Freeman, Josh Tenenbaum, Chelsea Finn, Jiajun Wu 0001	ICLR (Poster)	5
2019	Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning Anusha Nagabandi, Ignasi Clavera, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn	ICLR (Poster)	7
2019	Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL Anusha Nagabandi, Chelsea Finn, Sergey Levine	ICLR (Poster)	2
2019	Online Meta-Learning abstract A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the tasks are available together as a batch. In contrast, online (regret based) learning considers a setting where tasks are revealed one after the other, but conventionally trains a single model without task-specific adaptation. This work introduces an online meta-learning setting, which merges ideas from both paradigms to better capture the spirit and practice of continual lifelong learning. We propose the follow the meta leader (FTML) algorithm which extends the MAML algorithm to this setting. Theoretically, this work provides an O(log T) regret guarantee with one additional higher order smoothness assumption (in comparison to the standard online setting). Our experimental evaluation on three different large-scale problems suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches. Chelsea Finn, Aravind Rajeswaran, Sham M. Kakade, Sergey Levine	ICML	1
2019	Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables abstract Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While meta-reinforcement learning (meta-RL) algorithms can enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency. They also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness on sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-RL algorithm that disentangles task inference and control. In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience. This probabilistic interpretation enables posterior sampling for structured and efficient exploration. We demonstrate how to integrate these task variables with off-policy RL algorithms to achieve both meta-training and adaptation efficiency. Our method outperforms prior algorithms in sample efficiency by 20-100X as well as in asymptotic performance on several meta-RL benchmarks. Kate Rakelly, Aurick Zhou, Chelsea Finn, Sergey Levine, Deirdre Quillen	ICML	3
2019	Learning a Prior over Intent via Meta-Inverse Reinforcement Learning abstract A significant challenge for the practical application of reinforcement learning to real world problems is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert demonstrations. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly difficult to unambiguously recover a reward function. In this work, we exploit the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a "prior" that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. We demonstrate that our method can efficiently recover rewards from images for novel tasks and provide intuition as to how our approach is analogous to learning a prior. Kelvin Xu, Ellis Ratner, Anca D. Dragan, Sergey Levine, Chelsea Finn	ICML	5
2019	Manipulation by Feel: Touch-Based Control with Deep Predictive Models abstract Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading. Videos, visualizations and the code are available here: https://sites.google.com/view/deeptactilempc. Stephen Tian, Frederik Ebert, Dinesh Jayaraman, Mayur Mudigonda, Chelsea Finn, Roberto Calandra, Sergey Levine	ICRA	5
2019	One-Shot Composition of Vision-Based Skills from Demonstration abstract We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of major challenges. Video demonstrations without teleoperation are easy for humans to provide, but do not provide any direct supervision. Learning policies from raw pixels enables full generality but calls for large function approximators with many parameters to be learned. Finally, compound tasks can require impractical amounts of demonstration data, when treated as a monolithic skill. To address these challenges, we propose a method that learns both how to learn primitive behaviors from video demonstrations and how to dynamically compose these behaviors to perform multi-stage tasks by “watching” a human demonstrator. Our results on a simulated Sawyer robot and real PR2 robot illustrate our method for learning a variety of order fulfillment and kitchen serving tasks with novel objects and raw pixel inputs. Video results are linked at https://sites.google.com/view/one-shot-hil. Tianhe Yu, Pieter Abbeel, Sergey Levine, Chelsea Finn	IROS	4
2019	Unsupervised Curricula for Visual Meta-Reinforcement Learning abstract In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast and effective reinforcement learning (RL) strategies. However, current meta-RL approaches rely on manually-defined distributions of training tasks, and hand-crafting these task distributions can be challenging and time-consuming. Can ``useful'' pre-training tasks be discovered in an unsupervised manner? We develop an unsupervised algorithm for inducing an adaptive meta-training task distribution, i.e. an automatic curriculum, by modeling unsupervised interaction in a visual environment. The task distribution is scaffolded by a parametric density model of the meta-learner's trajectory distribution. We formulate unsupervised meta-RL as information maximization between a latent task variable and the meta-learner’s data distribution, and describe a practical instantiation which alternates between integration of recent experience into the task distribution and meta-learning of the updated tasks. Repeating this procedure leads to iterative reorganization such that the curriculum adapts as the meta-learner's data distribution shifts. Moreover, we show how discriminative clustering frameworks for visual representations can support trajectory-level task acquisition and exploration in domains with pixel observations, avoiding the pitfalls of alternatives. In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that both transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient meta-learning of test task distributions. Allan Jabri, Kyle Hsu, Abhishek Gupta 0004, Benjamin Eysenbach, Sergey Levine, Chelsea Finn	NeurIPS	6
2019	Language as an Abstraction for Hierarchical Deep Reinforcement Learning abstract Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn sub-skills that can be composed to solve longer tasks, i.e. hierarchical RL, we can acquire temporally-extended behaviors. However, acquiring effective yet general abstractions for hierarchical RL is remarkably challenging. In this paper, we propose to use language as the abstraction, as it provides unique compositional structure, enabling fast learning and combinatorial generalization, while retaining tremendous flexibility, making it suitable for a variety of problems. Our approach learns an instruction-following low-level policy and a high-level policy that can reuse abstractions across tasks, in essence, permitting agents to reason using structured language. To study compositional task learning, we introduce an open-source object interaction environment built using the MuJoCo physics engine and the CLEVR engine. We find that, using our approach, agents can learn to solve to diverse, temporally-extended tasks such as object sorting and multi-object rearrangement, including from raw pixel observations. Our analysis find that the compositional nature of language is critical for learning and systematically generalizing sub-skills in comparison to non-compositional abstractions that use the same supervision. Yiding Jiang, Shixiang Gu, Chelsea Finn	NeurIPS	4
2019	Guided Meta-Policy Search abstract Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples because they learn from scratch. Meta-RL aims to address this challenge by leveraging experience from previous tasks so as to more quickly solve new tasks. However, in practice, these algorithms generally also require large amounts of on-policy experience during the \emph{meta-training} process, making them impractical for use in many problems. To this end, we propose to learn a reinforcement learning procedure in a federated way, where individual off-policy learners can solve the individual meta-training tasks, and then consolidate these solutions into a single meta-learner. Since the central meta-learner learns by imitating the solutions to the individual tasks, it can accommodate either the standard meta-RL problem setting, or a hybrid setting where some or all tasks are provided with example demonstrations. The former results in an approach that can leverage policies learned for previous tasks without significant amounts of on-policy data during meta-training, whereas the latter is particularly useful in cases where demonstrations are easy for a person to provide. Across a number of continuous control meta-RL problems, we demonstrate significant improvements in meta-RL sample efficiency in comparison to prior work as well as the ability to scale to domains with visual observations. Russell Mendonca, Abhishek Gupta 0004, Rosen Kralev, Pieter Abbeel, Sergey Levine, Chelsea Finn	NeurIPS	6
2019	Meta-Learning with Implicit Gradients abstract A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this formulation, meta-parameters are learned in the outer loop, while task-specific models are learned in the inner-loop, by using only a small amount of data from the current task. A key challenge in scaling these approaches is the need to differentiate through the inner loop learning process, which can impose considerable computational and memory burdens. By drawing upon implicit differentiation, we develop the implicit MAML algorithm, which depends only on the solution to the inner level optimization and not the path taken by the inner loop optimizer. This effectively decouples the meta-gradient computation from the choice of inner loop optimizer. As a result, our approach is agnostic to the choice of inner loop optimizer and can gracefully handle many gradient steps without vanishing gradients or memory constraints. Theoretically, we prove that implicit MAML can compute accurate meta-gradients with a memory footprint that is, up to small constant factors, no more than that which is required to compute a single inner loop gradient and at no overall increase in the total computational cost. Experimentally, we show that these benefits of implicit MAML translate into empirical gains on few-shot image recognition benchmarks. Aravind Rajeswaran, Chelsea Finn, Sham M. Kakade, Sergey Levine	NeurIPS	2
2019	Meta-Inverse Reinforcement Learning with Probabilistic Context Variables abstract Reinforcement learning demands a reward function, which is often difficult to provide or design in real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions from scratch, requiring large numbers of demonstrations to correctly infer the reward for each task the agent may need to perform. Second, and more subtly, existing methods typically assume demonstrations for one, isolated behavior or task, while in practice, it is significantly more natural and scalable to provide datasets of heterogeneous behaviors. To this end, we propose a deep latent variable model that is capable of learning rewards from unstructured, multi-task demonstration data, and critically, use this experience to infer robust rewards for new, structurally-similar tasks from a single demonstration. Our experiments on multiple continuous control tasks demonstrate the effectiveness of our approach compared to state-of-the-art imitation and inverse reinforcement learning methods. Lantao Yu, Tianhe Yu, Chelsea Finn, Stefano Ermon	NeurIPS	3
2018	Stochastic Variational Video Prediction Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy H. Campbell, Sergey Levine	ICLR (Poster)	2
2018	Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm Chelsea Finn, Sergey Levine	ICLR (Poster)	1
2018	Recasting Gradient-Based Meta-Learning as Hierarchical Bayes Erin Grant, Chelsea Finn, Sergey Levine, Trevor Darrell, Thomas L. Griffiths 0001	ICLR (Poster)	2
2018	Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control abstract A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a forward model in a latent space and infers an optimal action plan through gradient descent trajectory optimization. The plan-by-gradient-descent process and its underlying representations are learned end-to-end to directly optimize a supervised imitation learning objective. We find that the representations learned are not only effective for goal-directed visual imitation via gradient-based trajectory optimization, but can also provide a metric for specifying goals using images. The learned representations can be leveraged to specify distance-based rewards to reach new target states for model-free reinforcement learning, resulting in substantially more effective learning when solving new tasks described via image based goals. We were able to achieve successful transfer of visuomotor planning strategies across robots with significantly different morphologies and actuation capabilities. Visit https://sites.google. com/view/upn-public/home for video highlights. Aravind Srinivas, Allan Jabri, Pieter Abbeel, Sergey Levine, Chelsea Finn	ICML	5
2018	Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods abstract In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best suited for a rich, diverse task like grasping. To answer this question, we propose a simulated benchmark for robotic grasping that emphasizes off-policy learning and generalization to unseen objects. Off-policy learning enables utilization of grasping data over a wide variety of objects, and diversity is important to enable the method to generalize to new objects that were not seen during training. We evaluate the benchmark tasks against a variety of Q-function estimation methods, a method previously proposed for robotic grasping with deep neural network models, and a novel approach based on a combination of Monte Carlo return estimation and an off-policy correction. Our results indicate that several simple methods provide a surprisingly strong competitor to popular algorithms such as double Q-learning, and our analysis of stability sheds light on the relative tradeoffs between the algorithms1. Deirdre Quillen, Eric Jang, Ofir Nachum, Chelsea Finn, Julian Ibarz, Sergey Levine	ICRA	4
2018	Probabilistic Model-Agnostic Meta-Learning abstract Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a powerful prior can be meta-learned from a large number of prior tasks, a small dataset for a new task can simply be too ambiguous to acquire a single model (e.g., a classifier) for that task that is accurate. In this paper, we propose a probabilistic meta-learning algorithm that can sample models for a new task from a model distribution. Our approach extends model-agnostic meta-learning, which adapts to new tasks via gradient descent, to incorporate a parameter distribution that is trained via a variational lower bound. At meta-test time, our algorithm adapts via a simple procedure that injects noise into gradient descent, and at meta-training time, the model is trained such that this stochastic adaptation procedure produces samples from the approximate model posterior. Our experimental results show that our method can sample plausible classifiers and regressors in ambiguous few-shot learning problems. We also show how reasoning about ambiguity can also be used for downstream active learning problems. Chelsea Finn, Kelvin Xu, Sergey Levine	NeurIPS	1
2017	Generalizing Skills with Semi-Supervised Reinforcement Learning Chelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine	ICLR (Poster)	1
2017	Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks abstract We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies. Chelsea Finn, Pieter Abbeel, Sergey Levine	ICML	1
2017	Deep visual foresight for planning robot motion abstract A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of requesting human feedback. Model-based reinforcement learning holds the promise of enabling an agent to learn to predict the effects of its actions, which could provide flexible predictive models for a wide range of tasks and environments, without detailed human supervision. We develop a method for combining deep action-conditioned video prediction models with model-predictive control that uses entirely unlabeled training data. Our approach does not require a calibrated camera, an instrumented training set-up, nor precise sensing and actuation. Our results show that our method enables a real robot to perform nonprehensile manipulation - pushing objects - and can handle novel objects not seen during training. Chelsea Finn, Sergey Levine	ICRA	1
2017	Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states abstract Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without extensive manual engineering. However, robotic skill learning must typically make trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human demonstrations, instrumentation of the training environment, or extremely long training times. We propose a new reinforcement learning algorithm that can train general-purpose neural network policies with minimal human engineering, while still allowing for fast, efficient learning in stochastic environments. We build on the guided policy search (GPS) algorithm, which transforms the reinforcement learning problem into supervised learning from a computational teacher (without human demonstrations). In contrast to prior GPS methods, which require a consistent set of initial states to which the system must be reset after each episode, our approach can handle random initial states, allowing it to be used even when deterministic resets are impossible. We compare our method to existing policy search algorithms in simulation, showing that it can train high-dimensional neural network policies with the same sample efficiency as prior GPS methods, and can learn policies directly from image pixels. We also present real-world robot results that show that our method can learn manipulation policies with visual features and random initial states. William Montgomery, Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine	ICRA	3
2016	Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization abstract Reinforcement learning can acquire complex behaviors from high-level specifications. However, defining a cost function that can be optimized effectively and encodes the correct task is challenging in practice. We explore how inverse optimal control (IOC) can be used to learn behaviors from demonstrations, with applications to torque control of high-dimensional robotic systems. Our method addresses two key challenges in inverse optimal control: first, the need for informative features and effective regularization to impose structure on the cost, and second, the difficulty of learning the cost function under unknown dynamics for high-dimensional continuous systems. To address the former challenge, we present an algorithm capable of learning arbitrary nonlinear cost functions, such as neural networks, without meticulous feature engineering. To address the latter challenge, we formulate an efficient sample-based approximation for MaxEnt IOC. We evaluate our method on a series of simulated tasks and real-world robotic manipulation problems, demonstrating substantial improvement over prior methods both in terms of task complexity and sample efficiency. Chelsea Finn, Sergey Levine, Pieter Abbeel	ICML	1
2016	Deep spatial autoencoders for visuomotor learning abstract Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the configuration of task-relevant objects. We present an approach that automates state-space construction by learning a state representation directly from camera images. Our method uses a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill with these feature points using an efficient reinforcement learning method based on local linear models. The resulting controller reacts continuously to the learned feature points, allowing the robot to dynamically manipulate objects in the world with closed-loop control. We demonstrate our method with a PR2 robot on tasks that include pushing a free-standing toy block, picking up a bag of rice using a spatula, and hanging a loop of rope on a hook at various positions. In each task, our method automatically learns to track task-relevant objects and manipulate their configuration with the robot's arm. Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel	ICRA	1
2016	Learning deep neural network policies with continuous memory states abstract Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional, continuous systems, such as robotic manipulators. Our approach consists of augmenting the state and action space of the system with continuous-valued memory states that the policy can read from and write to. Learning general-purpose policies with this type of memory representation directly is difficult, because the policy must automatically figure out the most salient information to memorize at each time step. We show that, by decomposing this policy search problem into a trajectory optimization phase and a supervised learning phase through a method called guided policy search, we can acquire policies with effective memorization and recall strategies. Intuitively, the trajectory optimization phase chooses the values of the memory states that will make it easier for the policy to produce the right action in future states, while the supervised learning phase encourages the policy to use memorization actions to produce those memory states. We evaluate our method on tasks involving continuous control in manipulation and navigation settings, and show that our method can learn complex policies that successfully complete a range of tasks that require memory. Marvin Zhang, Zoe McCarthy, Chelsea Finn, Sergey Levine, Pieter Abbeel	ICRA	3
2016	Unsupervised Learning for Physical Interaction through Video Prediction abstract A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information. However, to scale real-world interaction learning to a variety of scenes and objects, acquiring labeled data becomes increasingly impractical. To learn about physical object motion without labels, we develop an action-conditioned video prediction model that explicitly models pixel motion, by predicting a distribution over pixel motion from previous frames. Because our model explicitly predicts motion, it is partially invariant to object appearance, enabling it to generalize to previously unseen objects. To explore video prediction for real-world interactive agents, we also introduce a dataset of 59,000 robot interactions involving pushing motions, including a test set with novel objects. In this dataset, accurate prediction of videos conditioned on the robot's future actions amounts to learning a "visual imagination" of different futures based on different courses of action. Our experiments show that our proposed method produces more accurate video predictions both quantitatively and qualitatively, when compared to prior methods. Chelsea Finn, Ian J. Goodfellow, Sergey Levine	NIPS	1
2016	Adapting Deep Visuomotor Representations with Weak Pairwise Constraints Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, Pieter Abbeel, Sergey Levine, Kate Saenko, Trevor Darrell	WAFR	4
2016	End-to-End Training of Deep Visuomotor Policies abstract Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-to-end provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by deep convolutional neural networks (CNNs) with 92,000 parameters, and are trained using a guided policy search method, which transforms policy search into supervised learning, with supervision provided by a simple trajectory-centric reinforcement learning method. We evaluate our method on a range of real-world manipulation tasks that require close coordination between vision and control, such as screwing a cap onto a bottle, and present simulated comparisons to a range of prior policy search methods. Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel	J. Mach. Learn. Res.	2
2015	Beyond lowest-warping cost action selection in trajectory transfer abstract We consider the problem of learning from demonstrations to manipulate deformable objects. Recent work [1], [2], [3] has shown promising results that enable robotic manipulation of deformable objects through learning from demonstrations. Their approach is able to generalize from a single demonstration to new test situations, and suggests a nearest neighbor approach to select a demonstration to adapt to a given test situation. Such a nearest neighbor approach, however, ignores important aspects of the problem: brittleness (versus robustness) of demonstrations when generalized through this process, and the extent to which a demonstration makes progress towards a goal. In this paper, we frame the problem of selecting which demonstration to transfer as an options Markov decision process (MDP). We present max-margin Q-function estimation: an approach to learn a Q-function from expert demonstrations. Our learned policies account for variability in robustness of demonstrations and the sequential nature of our tasks. We developed two knot-tying benchmarks to experimentally validate the effectiveness of our proposed approach. The selection strategy described in [2] achieves success rates of 70% and 54%, respectively. Our approach performs significantly better, with success rates of 88% and 76%, respectively. Dylan Hadfield-Menell, Alex X. Lee, Chelsea Finn, Eric Tzeng, Sandy H. Huang, Pieter Abbeel	ICRA	3
2015	Bridging text spotting and SLAM with junction features abstract Navigating in a previously unknown environment and recognizing naturally occurring text in a scene are two important autonomous capabilities that are typically treated as distinct. However, these two tasks are potentially complementary, (i) scene and pose priors can benefit text spotting, and (ii) the ability to identify and associate text features can benefit navigation accuracy through loop closures. Previous approaches to autonomous text spotting typically require significant training data and are too slow for real-time implementation. In this work, we propose a novel high-level feature descriptor, the “junction”, which is particularly well-suited to text representation and is also fast to compute. We show that we are able to improve SLAM through text spotting on datasets collected with a Google Tango, illustrating how location priors enable improved loop closure with text features. Hsueh-Cheng Wang, Chelsea Finn, Liam Paull, Michael Kaess, Ruth Rosenholtz, Seth J. Teller, John J. Leonard	IROS	2
2015	Sloop: A pattern retrieval engine for individual animal identification James Duyck, Chelsea Finn, Andy Hutcheon, Pablo Vera, Joaquín Salas, Sai Ravela	Pattern Recognit.	2