Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons in trajectory data to ensure reasonable policy performance. To meet this requirement, leveraging large, expressive models has become a popular choice in recent literature, which, however, comes at the cost of significantly increased computation and inference latency. Contradictory yet promising, we reveal that lightweight models as simple as shallow 2-layer MLPs, can also enjoy accurate dynamics consistency and significantly reduced sequential modeling errors against large expressive models by adopting a simple recursive planning scheme: recursively planning coarse-grained future sub-goals based on current and target information, and then executes the action with a goal-conditioned policy learned from data relabeled with these sub-goal ground truths. We term our method as Recursive Skip-Step Planning (RSP). Simple yet effective, RSP enjoys great efficiency improvements thanks to its lightweight structure, and substantially outperforms existing methods, reaching new SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks.

Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many crowd-sourced embodied datasets, their action spaces often exhibit significant heterogeneity due to distinct physical embodiment and control interfaces for different robots, causing substantial challenges in developing embodied foundation models using cross-domain data. In this paper, we introduce UniAct, a new embodied foundation modeling framework operating in a Universal Act ion Space. Our learned universal actions capture the generic atomic behaviors across diverse robots by exploiting their shared structural features, and enable enhanced cross-domain data utilization and cross-embodiment generalizations by eliminating the notorious heterogeneity. The universal actions can be efficiently translated back to heterogeneous actionable commands by simply adding embodiment-specific details, from which fast adaptation to new robots becomes simple and straightforward. Our 0.5B instantiation of Uni-Act reaches 14X larger SOTA embodied foundation models in extensive evaluations on various real-world and simulation robots, showcasing exceptional cross-embodiment control and adaptation capability, highlighting the crucial benefit of adopting universal actions. Project page: https://2toinf.github.io/UniAct/

Humans excel at reusing prior knowledge to address new challenges and developing skills while solving problems. This paradigm becomes increasingly popular in the development of autonomous agents, as it develops systems that can self-evolve in response to new challenges like human beings. However, previous methods suffer from limited training efficiency when expanding new skills and fail to fully leverage prior knowledge to facilitate new task learning. We propose Parametric Skill Expansion and Composition (PSEC), a new framework designed to iteratively evolve the agents' capabilities and efficiently address new challenges by maintaining a manageable skill library. This library can progressively integrate skill primitives as plug-and-play Low-Rank Adaptation (LoRA) modules in parameter-efficient finetuning, facilitating efficient and flexible skill expansion. This structure also enables the direct skill compositions in parameter space by merging LoRA modules that encode different skills, leveraging shared information across skills to effectively program new skills. Based on this, we propose a context-aware modular to dynamically activate different skills to collaboratively handle new tasks. Empowering diverse applications including multi-objective composition, dynamics shift, and continual policy shift, the results on D4RL, DSRL benchmarks, and the DeepMind Control Suite show that PSEC exhibits superior capacity to leverage prior knowledge to efficiently tackle new challenges, as well as expand its skill libraries to evolve the capabilities. Project website: https://ltlhuuu.github.io/PSEC/.

The recent advances in information technology and artificial intelligence have fueled a rapid expansion of the data center (DC) industry worldwide, accompanied by an immense appetite for electricity to power the DCs. In a typical DC, around 30-40% of the energy is spent on the cooling system rather than on computer servers, posing a pressing need for developing new energy-saving optimization technologies for DC cooling systems. However, optimizing such real-world industrial systems faces numerous challenges, including but not limited to a lack of reliable simulation environments, limited historical data, and stringent safety and control robustness requirements. In this work, we present a novel physics-informed offline reinforcement learning (RL) framework for energy efficiency optimization of DC cooling systems. The proposed framework models the complex dynamical patterns and physical dependencies inside a server room using a purposely designed graph neural network architecture that is compliant with the fundamental time-reversal symmetry. Because of its well-behaved and generalizable state-action representations, the model enables sample-efficient and robust latent space offline policy learning using limited real-world operational data. Our framework has been successfully deployed and verified in a large-scale production DC for closed-loop control of its air-cooling units (ACUs). We conducted a total of 2000 hours of short and long-term experiments in the production DC environment. The results show that our method achieves 14-21% energy savings in the DC cooling system, without any violation of the safety or operational constraints. We have also conducted a comprehensive evaluation of our approach in a real-world DC testbed environment. Our results have demonstrated the significant potential of offline RL in solving a broad range of data-limited, safety-critical real-world industrial control problems.

Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imitation learning methods often struggle to balance competing objectives and lack of safety assurance,due to limited adaptability and inadequacy in learning complex multi-modal behaviors commonly exhibited in human planning, not to mention their strong reliance on the fallback strategy with predefined rules. We propose a novel transformer-based Diffusion Planner for closed-loop planning, which can effectively model multi-modal driving behavior and ensure trajectory quality without any rule-based refinement. Our model supports joint modeling of both prediction and planning tasks under the same architecture, enabling cooperative behaviors between vehicles. Moreover, by learning the gradient of the trajectory score function and employing a flexible classifier guidance mechanism, Diffusion Planner effectively achieves safe and adaptable planning behaviors. Evaluations on the large-scale real-world autonomous planning benchmark nuPlan and our newly collected 200-hour delivery-vehicle driving dataset demonstrate that Diffusion Planner achieves state-of-the-art closed-loop performance with robust transferability in diverse driving styles.

Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy learning: substantial computational costs that hinder real-time deployment, and accumulated inaccuracies that can mislead action extraction. Planning with coarse-grained subgoals partially alleviates efficiency issues. However, their forward planning schemes can still result in off-task predictions due to accumulation errors, leading to misalignment with long-term goals. This raises a critical question: Can robotic planning be both efficient and accurate enough for real-time control in long-horizon, multi-stage tasks? To address this, we propose a **B**ackward **P**lanning scheme in **L**atent space (**LBP**), which begins by grounding the task into final latent goals, followed by recursively predicting intermediate subgoals closer to the current state. The grounded final goal enables backward subgoal planning to always remain aware of task completion, facilitating on-task prediction along the entire planning horizon. The subgoal-conditioned policy incorporates a learnable token to summarize the subgoal sequences and determines how each subgoal guides action extraction. Through extensive simulation and real-robot long-horizon experiments, we show that LBP outperforms existing fine-grained and forward planning methods, achieving SOTA performance. Project Page: [https://lbp-authors.github.io](https://lbp-authors.github.io).

Multimodal task specification is essential for enhanced robotic performance, where Cross-modality Alignment enables the robot to holistically understand complex task instructions. Directly annotating multimodal instructions for model training proves impractical, due to the sparsity of paired multimodal data. In this study, we demonstrate that by leveraging unimodal instructions abundant in real data, we can effectively teach robots to learn multimodal task specifications. First, we endow the robot with strong Crossmodality Alignment capabilities, by pretraining a robotic multimodal encoder using extensive out-of-domain data. Then, we employ two Collapse and Corrupt operations to further bridge the remaining modality gap in the learned multimodal representation. This approach projects different modalities of identical task goal as interchangeable representations, thus enabling accurate robotic operations within a well-aligned multimodal latent space. Evaluation across more than 130 tasks and 4000 evaluations on both simulated LIBERO benchmark and real robot platforms showcases the superior capabilities of our proposed framework, demonstrating significant potential in overcoming data constraints in robotic learning. Website: zh1hao.wang/Robo_MUTUAL

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can suffer from severe sim-to-real issues. Offline RL approaches although bypass the need for simulators, often pose demanding requirements on the size and quality of the offline datasets. The recently emerged hybrid offline-and-online RL provides an attractive framework that enables joint use of limited offline data and imperfect simulator for transferable policy learning. In this paper, we develop a new algorithm, called$\mathrm{H} 2 \mathrm{O}+$, which offers great flexibility to bridge various choices of offline and online learning methods, while also accounting for dynamics gaps between the real and simulation environments. Through extensive simulation and real-world robotics experiments, we demonstrate superior performance and flexibility of$\mathbf{H 2 O}+$over advanced cross-domain online and offline RL algorithms.

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the dependency on over-engineered architectures for representation fusion. However, brute-force implementation by simply stacking transformer blocks lacks a dedicated mechanism for modeling interactive behaviors that is common in real driving scenarios. The scarcity of interactive driving data further exacerbates this problem, leaving conventional imitation learning methods ill-equipped to capture high-value interactive behaviors. We propose Flow Planner, which tackles these problems through coordinated innovations in data modeling, model architecture, and learning scheme. Specifically, we first introduce fine-grained trajectory tokenization, which decomposes the trajectory into overlapping segments to decrease the complexity of whole trajectory modeling. With a sophisticatedly designed architecture, we achieve efficient temporal and spatial fusion of planning and scene information, to better capture interactive behaviors. In addition, the framework incorporates flow matching with classifier-free guidance for multi-modal behavior generation, which dynamically reweights agent interactions during inference to maintain coherent response strategies, providing a critical boost for interactive scenario understanding. Experimental results on the large-scale nuPlan dataset demonstrate that Flow Planner achieves state-of-the-art performance among learning-based approaches while effectively modeling interactive behaviors in complex driving scenarios.

The practical use of reinforcement learning (RL) requires handling diverse settings, including online, offline, and offline-to-online learning. Instead of developing separate algorithms for each setting, we propose Uni-RL, a unified model-free RL framework that addresses all these scenarios within a single formulation. Uni-RL builds on the Implicit Value Regularization (IVR) framework and generalizes its dataset behavior constraint to the constraint w.r.t a reference policy, yielding an unified value learning objective for general settings. The reference policy is chosen to be the target policy in the online setting and the behavior policy in the offline setting. Using an iteratively refined behavior policy solves the over-constrained problem of directly applying IVR in the online setting, it provides an implicit trust-region style update through the value function while being off-policy. Uni-RL also introduces an unified policy extraction objective that estimates in-sample policy gradient using only actions from the reference policy. This supports various policy classes and theoretically guaranntees less value estimation error and larger performance improvement over the reference policy. We evaluate Uni-RL on a range of standard RL benchmarks across online, offline, and offline-to-online settings. In online RL, Uni-RL achieves higher sample efficiency than both off-policy methods without trust-region updates and on-policy methods with trust-region updates. In offline RL, Uni-RL retains the benefits of in-sample learning while outperforming IVR through better policy extraction. In offline-to-online RL, Uni-RL beats both constraint-based methods and unconstrained approaches by effectively balancing stability and adaptability.

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward representations (FB) and related methods have shown promise in zero-shot RL, we empirically found that their modeling lacks expressivity and that extrapolation errors caused by out-of-distribution (OOD) actions during offline learning sometimes lead to biased representations, ultimately resulting in suboptimal performance. To address these issues, we propose Behavior-REgularizEd Zero-shot RL with Expressivity enhancement (BREEZE), an upgraded FB-based framework that simultaneously enhances learning stability, policy extraction capability, and representation learning quality. BREEZE introduces behavioral regularization in zero-shot RL policy learning, transforming policy optimization into a stable in-sample learning paradigm. Additionally, BREEZE extracts the policy using a task-conditioned diffusion model, enabling the generation of high-quality and multimodal action distributions in zero-shot RL settings. Moreover, BREEZE employs expressive attention-based architectures for representation modeling to capture the complex relationships between environmental dynamics. Extensive experiments on ExORL and D4RL Kitchen demonstrate that BREEZE achieves the best or near-the-best performance while exhibiting superior robustness compared to prior offline zero-shot RL methods. The official implementation is available at: https://github.com/Whiterrrrr/BREEZE.

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited labeled data to infer and utilize the hidden information from unlabeled data. We note that any semi-supervised learning task under the self-training paradigm also hides an auxiliary task of discriminating label observability. Jointly solving these two tasks allows full utilization of information from both labeled and unlabeled data, thus alleviating the problem of over-reliance on labeled data. This naturally leads to a new generic and efficient learning framework without the reliance on any domain-specific information, which we call FlexSSL. The key idea of FlexSSL is to construct a semi-cooperative “game”, which forges cooperation between a main self-interested semi-supervised learning task and a companion task that infers label observability to facilitate main task training. We show with theoretical derivation of its connection to loss re-weighting on noisy labels. Through evaluations on a diverse range of tasks, we demonstrate that FlexSSL can consistently enhance the performance of semi-supervised learning algorithms.

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents’ behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods focus on selecting queries to maximally improve the overall quality of the reward model, but counter-intuitively, we find that this may not necessarily lead to improved performance. To unravel this mystery, we identify a long-neglected issue in the query selection schemes of existing PbRL studies: Query-Policy Misalignment. We show that the seemingly informative queries selected to improve the overall quality of reward model actually may not align with RL agents’ interests, thus offering little help on policy learning and eventually resulting in poor feedback efficiency. We show that this issue can be effectively addressed via policy-aligned query and a specially designed hybrid experience replay, which together enforce the bidirectional query-policy alignment. Simple yet elegant, our method can be easily incorporated into existing approaches by changing only a few lines of code. We showcase in comprehensive experiments that our method achieves substantial gains in both human feedback and RL sample efficiency, demonstrating the importance of addressing query-policy misalignment in PbRL tasks.

In this study, we investigate the DIstribution Correction Estimation (DICE) methods, an important line of work in offline reinforcement learning (RL) and imitation learning (IL). DICE-based methods impose state-action-level behavior constraint, which is an ideal choice for offline learning. However, they typically perform much worse than current state-of-the-art (SOTA) methods that solely use action-level behavior constraint. After revisiting DICE-based methods, we find there exist two gradient terms when learning the value function using true-gradient update: forward gradient (taken on the current state) and backward gradient (taken on the next state). Using forward gradient bears a large similarity to many offline RL methods, and thus can be regarded as applying action-level constraint. However, directly adding the backward gradient may degenerate or cancel out its effect if these two gradients have conflicting directions. To resolve this issue, we propose a simple yet effective modification that projects the backward gradient onto the normal plane of the forward gradient, resulting in an orthogonal-gradient update, a new learning rule for DICE-based methods. We conduct thorough theoretical analyses and find that the projected backward gradient brings state-level behavior regularization, which reveals the mystery of DICE-based methods: the value learning objective does try to impose state-action-level constraint, but needs to be used in a corrected way. Through toy examples and extensive experiments on complex offline RL and IL tasks, we demonstrate that DICE-based methods using orthogonal-gradient updates achieve SOTA performance and great robustness.

Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://github.com/imoneoi/openchat and https://huggingface.co/openchat.

Safe offline reinforcement learning is a promising way to bypass risky online interactions towards safe policy learning. Most existing methods only enforce soft constraints, i.e., constraining safety violations in expectation below thresholds predetermined. This can lead to potentially unsafe outcomes, thus unacceptable in safety-critical scenarios. An alternative is to enforce the hard constraint of zero violation. However, this can be challenging in offline setting, as it needs to strike the right balance among three highly intricate and correlated aspects: safety constraint satisfaction, reward maximization, and behavior regularization imposed by offline datasets. Interestingly, we discover that via reachability analysis of safe-control theory, the hard safety constraint can be equivalently translated to identifying the largest feasible region given the offline dataset. This seamlessly converts the original trilogy problem to a feasibility-dependent objective, i.e., maximizing reward value within the feasible region while minimizing safety risks in the infeasible region. Inspired by these, we propose FISOR (FeasIbility-guided Safe Offline RL), which allows safety constraint adherence, reward maximization, and offline policy learning to be realized via three decoupled processes, while offering strong safety performance and stability. In FISOR, the optimal policy for the translated optimization problem can be derived in a special form of weighted behavior cloning, which can be effectively extracted with a guided diffusion model thanks to its expressiveness. We compare FISOR against baselines on DSRL benchmark for safe offline RL. Evaluation results show that FISOR is the only method that can guarantee safety satisfaction in all tasks, while achieving top returns in most tasks. Code: https://github.com/ZhengYinan-AIR/FISOR.

Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on addressing the value overestimation issue, an outcome of adopting function approximators and off-policy learning. Deviating from the common viewpoint, we observe that $Q$-values are often underestimated in the latter stage of the RL training process, potentially hindering policy learning and reducing sample efficiency. We find that such a long-neglected phenomenon is often related to the use of inferior actions from the current policy in Bellman updates as compared to the more optimal action samples in the replay buffer. We propose the Blended Exploitation and Exploration (BEE) operator, a simple yet effective approach that updates $Q$-value using both historical best-performing actions and the current policy. Based on BEE, the resulting practical algorithm BAC outperforms state-of-the-art methods in over 50 continuous control tasks and achieves strong performance in failure-prone scenarios and real-world robot tasks. Benchmark results and videos are available at https://jity16.github.io/BEE/.

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: $1)$ extracting both local and global task progressions; $2)$ enforcing temporal consistency of visual representation; $3)$ capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/

Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or dynamics shifts, or rely on specialized algorithms with task priors, thus often resulting in suboptimal policy performances and high learning variances. In this paper, we identify a unified strategy for online RL policy learning under diverse settings of policy and dynamics shifts: transition occupancy matching. In light of this, we introduce a surrogate policy learning objective by considering the transition occupancy discrepancies and then cast it into a tractable min-max optimization problem through dual reformulation. Our method, dubbed Occupancy-Matching Policy Optimization (OMPO), features a specialized actor-critic structure equipped with a distribution discriminator and a small-size local buffer. We conduct extensive experiments based on the OpenAI Gym, Meta-World, and Panda Robots environments, encompassing policy shifts under stationary and non-stationary dynamics, as well as domain adaption. The results demonstrate that OMPO outperforms the specialized baselines from different categories in all settings. We also find that OMPO exhibits particularly strong performance when combined with domain randomization, highlighting its potential in RL-based robotics applications.

Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally exploit the information in the replay buffer, limiting sample efficiency and policy performance. In this work, we discover that concurrently training an offline RL policy based on the shared online replay buffer can sometimes outperform the original online learning policy, though the occurrence of such performance gains remains uncertain. This motivates a new possibility of harnessing the emergent outperforming offline optimal policy to improve online policy learning. Based on this insight, we present Offline-Boosted Actor-Critic (OBAC), a model-free online RL framework that elegantly identifies the outperforming offline policy through value comparison, and uses it as an adaptive constraint to guarantee stronger policy learning performance. Our experiments demonstrate that OBAC outperforms other popular model-free RL baselines and rivals advanced model-based RL methods in terms of sample efficiency and asymptotic performance across **53** tasks spanning **6** task suites.

The increasing demand for artificial intelligence and cloud computing has led to skyrocketing energy consumption of data centers (DCs). This paper focuses on tackling this energy challenge through cooling control system optimization, which aims to ensure thermal safety with minimal cooling energy consumption. Current industry practice involves human operators, while many data-driven methods have also been proposed. However, human intervention often results in unnecessary energy consumption, particularly in the face of fluctuating server loads, whereas existing data-driven methods struggle to maintain thermal safety in practice. To overcome these issues, we propose TESLA, a thermally safe, load-aware, and energy-efficient cooling control system for data centers. TESLA employs a novel data-driven framework that integrates domain knowledge to predict DC temperature and cooling energy under dynamic server load. Based on these predictions, a Bayesian optimizer (BO) finds the energy-optimal settings for the cooling system at every control step. Besides cooling energy, BO’s optimization objective also includes minimizing cooling interruption that causes rapid temperature rise within the data center and leads to thermal safety violations. We deploy TESLA on a real data-center testbed and show that it achieves on average <?TeX $10.1\%$?> Math 1 cooling energy saving relative to a fixed cooling system parameter setting and no thermal safety violation relative to previous data-driven methods.

One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collection policy. In this work, we show that DICE-based methods can be viewed as a transformation from the behavior distribution to the optimal policy distribution. Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models. We find that the optimal policy's score function can be decomposed into two terms: the behavior policy's score function and the gradient of a guidance term which depends on the optimal distribution ratio. The first term can be obtained from a diffusion model trained on the dataset and we propose an in-sample learning objective to learn the second term. Due to the multi-modality contained in the optimal policy distribution, the transformation in Diffusion-DICE may guide towards those local-optimal modes. We thus generate a few candidate actions and carefully select from them to achieve global-optimum. Different from all other diffusion-based offline RL methods, the \textit{guide-then-select} paradigm in Diffusion-DICE only uses in-sample actions for training and brings minimal error exploitation in the value function. We use a didatic toycase example to show how previous diffusion-based methods fail to generate optimal actions due to leveraging these errors and how Diffusion-DICE successfully avoid that. We then conduct extensive experiments on benchmark datasets to show the strong performance of Diffusion-DICE.

Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and nuanced multimodal instruction following, we introduce Instruction-guided Visual Masking (IVM), a new versatile visual grounding model that is compatible with diverse multimodal models, such as LMM and robot model. By constructing visual masks for instruction-irrelevant regions, IVM-enhanced multimodal models can effectively focus on task-relevant image regions to better align with complex instructions. Specifically, we design a visual masking data generation pipeline and create an IVM-Mix-1M dataset with 1 million image-instruction pairs. We further introduce a new learning technique, Discriminator Weighted Supervised Learning (DWSL) for preferential IVM training that prioritizes high-quality data samples. Experimental results on generic multimodal tasks such as VQA and embodied robotic control demonstrate the versatility of IVM, which as a plug-and-play tool, significantly boosts the performance of diverse multimodal models, yielding new state-of-the-art results across challenging multimodal benchmarks. Code, model and data are available at https://github.com/2toinf/IVM.

Offline reinforcement learning (RL) enables learning policies from precollected datasets without online data collection. Although it offers the possibility to surpass the performance of the datasets, most existing offline RL algorithms struggle to compete with behavior cloning policies in many dataset settings due to trading off policy improvement and additional regularization to address the distributional shift issue. In many cases, if one can imitate a sequence of suboptimal subtrajectories in data and properly“stitch”them toward reaching an ideal future state, it may potentially result in a more reliable policy while avoiding difficulties that present in typical value-based offline RL algorithms. We borrow the idea of curriculum learning to embody the above intuition. We construct a curriculum that progressively imitates a sequence of suboptimal trajectories conditioned on a series of carefully constructed future states and cumulative rewards as goals. The suboptimal trajectories gradually guide policy learning toward reaching the ideal goal states. We name our algorithm curriculum goal-conditioned imitation (CGI). Experimental results show that CGI achieves competitive performance against state-of-the-art offline RL algorithms, especially for challenging tasks with long horizons and sparse rewards.

Beamforming plays an important role in 5G Massive Multiple-Input Multiple-Output (MMIMO) communications. Optimizing beamforming configurations for 5G base stations (BSs) can substantially improve the quality of service for mobile users, and thus has great practical value. However, identifying the optimal beamforming configurations has proven to be a complex task, and is even more challenging when accounting for the unavoidable coupled influence among multiple densely deployed 5G BSs. In this paper, we propose a highly efficient deep multi-agent Bayesian optimization framework for the coordinated beamforming optimization problem that involves multiple BSs. Its core algorithm is built upon a deep ensemble of neural networks and a sample-efficient upper confidence bound (UCB) based exploration strategy. Our numerical results show that the proposed approach is highly effective in searching for optimally coordinated beamforming vectors under extremely large search space, and beats strong multi-agent reinforcement learning baselines in terms of optimization quality and sample efficiency.

Offline reinforcement learning (RL) offers an appealing approach to real-world tasks by learning policies from pre-collected datasets without interacting with the environment. However, the performance of existing offline RL algorithms heavily depends on the scale and state-action space coverage of datasets. Real-world data collection is often expensive and uncontrollable, leading to small and narrowly covered datasets and posing significant challenges for practical deployments of offline RL. In this paper, we provide a new insight that leveraging the fundamental symmetry of system dynamics can substantially enhance offline RL performance under small datasets. Specifically, we propose a Time-reversal symmetry (T-symmetry) enforced Dynamics Model (TDM), which establishes consistency between a pair of forward and reverse latent dynamics. TDM provides both well-behaved representations for small datasets and a new reliability measure for OOD samples based on compliance with the T-symmetry. These can be readily used to construct a new offline RL algorithm (TSRL) with less conservative policy constraints and a reliable latent space data augmentation procedure. Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability. Code is available at: https://github.com/pcheng2/TSRL

Offline reinforcement learning (RL) has received considerable attention in recent years due to its attractive capability of learning policies from offline datasets without environmental interactions. Despite some success in the single-agent setting, offline multi-agent RL (MARL) remains to be a challenge. The large joint state-action space and the coupled multi-agent behaviors pose extra complexities for offline policy optimization. Most existing offline MARL studies simply apply offline data-related regularizations on individual agents, without fully considering the multi-agent system at the global level. In this work, we present OMIGA, a new offline multi-agent RL algorithm with implicit global-to-local value regularization. OMIGA provides a principled framework to convert global-level value regularization into equivalent implicit local value regularizations and simultaneously enables in-sample learning, thus elegantly bridging multi-agent value decomposition and policy learning with offline regularizations. Based on comprehensive experiments on the offline multi-agent MuJoCo and StarCraft II micro-management tasks, we show that OMIGA achieves superior performance over the state-of-the-art offline MARL methods in almost all tasks.

Detecting anomalies in large complex systems is a critical and challenging task. The difficulties arise from several aspects. First, collecting ground truth labels or prior knowledge for anomalies is hard in real-world systems, which often lead to limited or no anomaly labels in the dataset. Second, anomalies in large systems usually occur in a collective manner due to the underlying dependency structure among devices or sensors. Lastly, real-time anomaly detection for high-dimensional data requires efficient algorithms that are capable of handling different types of data (i.e. continuous and discrete). We propose a correlation structure-based collective anomaly detection (CSCAD) model for high-dimensional anomaly detection problem in large systems, which is also generalizable to semi-supervised or supervised settings. Our framework utilize graph convolutional network combining a variational autoencoder to jointly exploit the feature space correlation and reconstruction deficiency of samples to perform anomaly detection. We propose an extended mutual information (EMI) metric to mine the internal correlation structure among different data features, which enhances the data reconstruction capability of CSCAD. The reconstruction loss and latent standard deviation vector of a sample obtained from reconstruction network can be perceived as two natural anomalous degree measures. An anomaly discriminating network can then be trained using low anomalous degree samples as positive samples, and high anomalous degree samples as negative samples. Experimental results on five public datasets demonstrate that our approach consistently outperforms all the competing baselines.

Improving the efficiency of coal-fired power plants has numerous benefits. The control strategy is one of the major factors affecting such efficiency. However, due to the complex and dynamic environment inside the power plants, it is hard to extract and evaluate control strategies and their cascading impact across massive sensors. Existing manual and data-driven approaches cannot well support the analysis of control strategies because these approaches are time-consuming and do not scale with the complexity of the power plant systems. Three challenges were identified: a) interactive extraction of control strategies from large-scale dynamic sensor data, b) intuitive visual representation of cascading impact among the sensors in a complex power plant system, and c) time-lag-aware analysis of the impact of control strategies on electricity generation efficiency. By collaborating with energy domain experts, we addressed these challenges with ECoalVis, a novel interactive system for experts to visually analyze the control strategies of coal-fired power plants extracted from historical sensor data. The effectiveness of the proposed system is evaluated with two usage scenarios on a real-world historical dataset and received positive feedback from experts.

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment. This problem is more appealing for real world RL applications, in which data collection is costly or dangerous. Enforcing constraint satisfaction is non-trivial, especially in offline settings, as there is a potential large discrepancy between the policy distribution and the data distribution, causing errors in estimating the value of safety constraints. We show that naïve approaches that combine techniques from safe RL and offline RL can only learn sub-optimal solutions. We thus develop a simple yet effective algorithm, Constraints Penalized Q-Learning (CPQ), to solve the problem. Our method admits the use of data generated by mixed behavior policies. We present a theoretical analysis and demonstrate empirically that our approach can learn robustly across a variety of benchmark control tasks, outperforming several baselines.

Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry. We develop a new data-driven AI system, namely DeepThermal, to optimize the combustion control strategy for TPGUs. At its core, is a new model-based offline reinforcement learning (RL) framework, called MORE, which leverages historical operational data of a TGPU to solve a highly complex constrained Markov decision process problem via purely offline training. In DeepThermal, we first learn a data-driven combustion process simulator from the offline dataset. The RL agent of MORE is then trained by combining real historical data as well as carefully filtered and processed simulation data through a novel restrictive exploration scheme. DeepThermal has been successfully deployed in four large coal-fired thermal power plants in China. Real-world experiments show that DeepThermal effectively improves the combustion efficiency of TPGUs. We also report the superior performance of MORE by comparing with the state-of-the-art algorithms on the standard offline RL benchmarks.

We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset from suboptimal behaviors. Prior works that address this problem either require that expert data occupies the majority proportion of the offline dataset, or need to learn a reward function and perform offline reinforcement learning (RL) afterwards. In this paper, we aim to address the problem without additional steps of reward learning and offline RL training for the case when demonstrations contain a large proportion of suboptimal data. Built upon behavioral cloning (BC), we introduce an additional discriminator to distinguish expert and non-expert data. We propose a cooperation framework to boost the learning of both tasks, Based on this framework, we design a new IL algorithm, where the outputs of the discriminator serve as the weights of the BC loss. Experimental results show that our proposed algorithm achieves higher returns and faster training speed compared to baseline algorithms.

The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL methods still face many practical challenges in real-world system control tasks, such as computational restriction during agent training and the requirement of extra control flexibility. The model-based planning framework provides an attractive alternative. However, most model-based planning algorithms are not designed for offline settings. Simply combining the ingredients of offline RL with existing methods either provides over-restrictive planning or leads to inferior performance. We propose a new light-weighted model-based offline planning framework, namely MOPP, which tackles the dilemma between the restrictions of offline learning and high-performance planning. MOPP encourages more aggressive trajectory rollout guided by the behavior policy learned from data, and prunes out problematic trajectories to avoid potential out-of-distribution samples. Experimental results show that MOPP provides competitive performance compared with existing model-based offline planning and RL approaches.

Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we are only given imperfect simulators with simplified dynamics, which inevitably lead to severe sim-to-real gaps in RL policy learning. The recently emerged field of offline RL provides another possibility to learn policies directly from pre-collected historical data. However, to achieve reasonable performance, existing offline RL algorithms need impractically large offline data with sufficient state-action space coverage for training. This brings up a new question: is it possible to combine learning from limited real data in offline RL and unrestricted exploration through imperfect simulators in online RL to address the drawbacks of both approaches? In this study, we propose the Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning (H2O) framework to provide an affirmative answer to this question. H2O introduces a dynamics-aware policy evaluation scheme, which adaptively penalizes the Q function learning on simulated state-action pairs with large dynamics gaps, while also simultaneously allowing learning from a fixed real-world dataset. Through extensive simulation and real-world tasks, as well as theoretical analysis, we demonstrate the superior performance of H2O against other cross-domain online and offline RL algorithms. H2O provides a brand new hybrid offline-and-online RL paradigm, which can potentially shed light on future RL algorithm design for solving practical real-world tasks.

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy evaluation. Imitation-based methods avoid off-policy evaluation but are too conservative to surpass the dataset. In this study, we propose an alternative approach, inheriting the training stability of imitation-style methods while still allowing logical out-of-distribution generalization. We decompose the conventional reward-maximizing policy in offline RL into a guide-policy and an execute-policy. During training, the guide-poicy and execute-policy are learned using only data from the dataset, in a supervised and decoupled manner. During evaluation, the guide-policy guides the execute-policy by telling where it should go so that the reward can be maximized, serving as the \textit{Prophet}. By doing so, our algorithm allows \textit{state-compositionality} from the dataset, rather than \textit{action-compositionality} conducted in prior imitation-style methods. We dumb this new approach Policy-guided Offline RL (\texttt{POR}). \texttt{POR} demonstrates the state-of-the-art performance on D4RL, a standard benchmark for offline RL. We also highlight the benefits of \texttt{POR} in terms of improving with supplementary suboptimal data and easily adapting to new tasks by only changing the guide-poicy.

Purchase prediction is an essential task in both online and offline retail industry, especially during major shopping festivals, when strong promotion boosts consumption dramatically. It is important for merchants to forecast such surge of sales and have better preparation. This is a challenging problem, as the purchase patterns during shopping festivals are significantly different from usual cases and also rare in historical data. Most existing methods fail at this problem due to the extremely scarce data samples as well as the inability to capture the complex macroscopic spatio-temporal dependencies in a city. To address this problem, we propose the Spatio-Temporal Meta-learning Prediction (STMP) model for purchase prediction during shopping festivals. STMP is a meta-learning based spatio-temporal multi-task deep generative model. It adopts a meta-learning framework with few-shot learning capability to capture both spatial and temporal data representations. A generative component then uses the extracted spatio-temporal representation and input data to infer the prediction results. Extensive experiments demonstrate the meta-learning generalization ability of STMP. STMP outperforms baselines in all cases, which shows the effectiveness of our model.

Accurate network-wide traffic state estimation is vital to many transportation operations and urban applications. However, existing methods often suffer from the scalability issue when performing real-time inference at the city-level, or not robust enough under limited data. Currently, GPS trajectory data from probe vehicles has become a popular data source for many transportation applications. GPS trajectory data has large coverage area, which is ideal for network-wide applications, but also has the disadvantage of being sparse and highly heterogeneous among different time and locations. In this study, we focus on developing a robust and interpretable network-wide traffic state imputation framework using partially observed traffic information. We introduce a new learning strategy, called self-interested coalitional learning (SCL), which forges cooperation between a main self-interested semi-supervised learning task and a discriminator as a critic to facilitate main task training while providing interpretability on the results. In our detailed model, we use a temporal graph convolutional variational autoencoder (TG-VAE) as the reconstructor, which models the complex spatio-temporal pattern in data and solves the main traffic state imputation task. A discriminator is introduced to output interpretable imputation confidence on the estimated results and also help to enhance the performance of the reconstructor. The framework is evaluated using a large GPS trajectory dataset from taxis in Jinan, China. Extensive experiments against the state-of-the-art baselines demonstrate the effectiveness and robustness of the proposed method for network-wide traffic state estimation.

Traffic volume estimation at the city scale is an important problem useful to many transportation operations and urban applications. This paper proposes a hybrid framework that integrates both state-of-art machine learning techniques and well-established traffic flow theory to estimate citywide traffic volume. In addition to typical urban context features extracted from multiple sources, we extract a special set of features from GPS trajectories based on the implications of traffic flow theory, which provide extra information on the speed-flow relationship. Using the network-wide speed information estimated from a travel speed estimation model, a volume related high level feature is first learned using an unsupervised graphical model. A volume re-interpretation model is then introduced to map the volume related high level feature to the predicted volume using a small amount of ground truth data for training. The framework is evaluated using a GPS trajectory dataset from 33,000 Beijing taxis and volume ground truth data obtained from 4,980 video clips. The results demonstrate effectiveness and potential of the proposed framework in citywide traffic volume estimation.

Taxi service systems in big cities are immensely complex due to the interaction and self-organization between taxi drivers and passengers. An inefficient taxi service system leads to more empty trips for drivers and longer waiting time for passengers and introduces unnecessary congestion on the road network. In this paper, we investigate the efficiency level of the taxi service system using real-world large-scale taxi trip data. By assuming a hypothetical system-wide recommendation system, two approaches are proposed to find the theoretical optimal strategies that minimize the cost of empty trips and the number of taxis required to satisfy all the observed trips. The optimization problems are transformed into equivalent graph problems and solved using polynomial time algorithms. The taxi trip data in New York City are used to quantitatively examine the gap between the current system performance and the theoretically optimal system. The numerical results indicate that, if system-wide information between taxi drivers and passengers was shared, it is possible to reduce 60%-90% of the total empty trip cost depending on different objectives, and one-third of all taxis required to serve all observed trips. The existence of destructive competition among taxi drivers is also uncovered in the actual taxi service system. The huge performance gap suggests an urgent need for a system reconsideration in designing taxi recommendation systems.