In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the underlying decision dynamics. In contrast, large language models (LLMs) have recently emerged as powerful general-purpose tools, due to their capacity to maintain vast amounts of domain-specific knowledge. To harness this rich prior knowledge for efficiently solving complex SDM tasks, we propose treating LLMs as prior action distributions and integrating them into RL frameworks through Bayesian inference methods, making use of variational inference and direct posterior sampling. The proposed approaches facilitate the seamless incorporation of fixed LLM priors into both policy-based and value-based RL frameworks. Our experiments show that incorporating LLM-based action priors significantly reduces exploration and optimization complexity, substantially improving sample efficiency compared to traditional RL techniques, e.g., using LLM priors decreases the number of required samples by over 90\% in offline learning scenarios.

While Generative AI rapidly advances in various domains, generating truly creative, aesthetic, and counter-intuitive outputs remains a challenge. This paper presents an approach to tackle these difficulties in the domain of chess puzzles. We start by benchmarking Generative AI architectures, and then introduce an RL framework with novel rewards based on chess engine search statistics to overcome some of those shortcomings. The rewards are designed to enhance a puzzle's uniqueness, counter-intuitiveness, diversity, and realism. Our RL approach dramatically increases counter-intuitive puzzle generation by 10x, from 0.22\% (supervised) to 2.5\%, surpassing existing dataset rates (2.1\%) and the best Lichess-trained model (0.4\%). Our puzzles meet novelty and diversity benchmarks, retain aesthetic themes, and are rated by human experts as more creative, enjoyable, and counter-intuitive than composed book puzzles, even approaching classic compositions. Our final outcome is a curated booklet of these novel AI-generated puzzles, which is acknowledged for creativity by three world-renowned experts.

Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the multi-step reasoning capabilities of LLMs by using tree-search algorithms. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a result, these methods cannot benefit from in-domain training and only rely on pretraining process — they will not work in domains where the pre-trained LLM does not have enough knowledge to serve as an effective value function or in domains that require long-horizon planning. To address these limitations, we present an AlphaZero-like tree-search learning framework for LLMs (termed TS-LLM), systematically illustrating how tree-search with a learned value function can guide LLM decoding. TS-LLM distinguishes itself in two key ways. (1) Leveraging a learned value function and AlphaZero-like algorithms, our approach can be generally adaptable to a wide range of tasks, language models of any size, and tasks of varying search depths. (2) Our approach can guide LLMs during both inference and training, iteratively improving the LLMs. Empirical results across reasoning, planning, alignment, and decision-making tasks show that TS-LLM outperforms existing approaches and can handle trees with a depth of 64.

In the face of uncertainty, the ability to *seek information* is of fundamental importance. In many practical applications, such as medical diagnosis and troubleshooting, the information needed to solve the task is not initially given, and has to be actively sought by asking follow-up questions (for example, a doctor asking a patient for more details about their symptoms). In this work, we introduce **Uncertainty of Thoughts (UoT)**, an algorithm to augment large language models with the ability to actively seek information by asking effective questions. UoT combines: 1. An *uncertainty-aware simulation approach* which enables the model to simulate possible future scenarios and how likely they are to occur, 2. *Uncertainty-based rewards* motivated by information gain which incentivizes the model to seek information, and 3. A *reward propagation scheme* to select the optimal question to ask in a way that maximizes the expected reward. In experiments on medical diagnosis, troubleshooting and the `20 Questions' game, UoT achieves an average performance improvement of 38.1% in the rate of successful task completion across multiple LLMs compared with direct prompting, and also improves efficiency (i.e., the number of questions needed to complete the task).

The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in AI research. However, many research endeavours heavily rely on parameter sharing among agents, which confines them to only homogeneous-agent setting and leads to training instability and lack of convergence guarantees. To achieve effective cooperation in the general heterogeneous-agent setting, we propose Heterogeneous-Agent Reinforcement Learning (HARL) algorithms that resolve the aforementioned issues. Central to our findings are the multi-agent advantage decomposition lemma and the sequential update scheme. Based on these, we develop the provably correct Heterogeneous-Agent Trust Region Learning (HATRL), and derive HATRPO and HAPPO by tractable approximations. Furthermore, we discover a novel framework named Heterogeneous-Agent Mirror Learning (HAML), which strengthens theoretical guarantees for HATRPO and HAPPO and provides a general template for cooperative MARL algorithmic designs. We prove that all algorithms derived from HAML inherently enjoy monotonic improvement of joint return and convergence to Nash Equilibrium. As its natural outcome, HAML validates more novel algorithms in addition to HATRPO and HAPPO, including HAA2C, HADDPG, and HATD3, which generally outperform their existing MA-counterparts. We comprehensively test HARL algorithms on six challenging benchmarks and demonstrate their superior effectiveness and stability for coordinating heterogeneous agents compared to strong baselines such as MAPPO and QMIX.

In multi-agent reinforcement learning (MARL), independent learning (IL) often shows remarkable performance and easily scales with the number of agents. Yet, using IL can be inefficient and runs the risk of failing to successfully train, particularly in scenarios that require agents to coordinate their actions. Using centralised learning (CL) enables MARL agents to quickly learn how to coordinate their behaviour but employing CL everywhere is often prohibitively expensive in real-world applications. Besides, using CL in value-based methods often needs strong representational constraints (e.g. individual-global-max condition) that can lead to poor performance if violated. In this paper, we introduce a novel plug & play IL framework named Multi-Agent Network Selection Algorithm (MANSA) which selectively employs CL only at states that require coordination. At its core, MANSA has an additional agent that uses switching controls to quickly learn the best states to activate CL during training, using CL only where necessary and vastly reducing the computational burden of CL. Our theory proves MANSA preserves cooperative MARL convergence properties, boosts IL performance and can optimally make use of a fixed budget on the number CL calls. We show empirically in Level-based Foraging (LBF) and StarCraft Multi-agent Challenge (SMAC) that MANSA achieves fast, superior and more reliable performance while making 40% fewer CL calls in SMAC and using CL at only 1% CL calls in LBF.

When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the invaluable thought process or strategic considerations. Despite this, the majority of preceding research focuses on only one source: they either use historical replay exclusively to directly learn policy or value functions, or engaged in language model training utilizing mere language corpus. In this paper, we argue that a powerful autonomous agent should cover both sources. Thus, we propose ChessGPT, a GPT model bridging policy learning and language modeling by integrating data from these two sources in Chess games. Specifically, we build a large-scale game and language dataset related to chess. Leveraging the dataset, we showcase two model examples ChessCLIP and ChessGPT, integrating policy learning and language modeling. Finally, we propose a full evaluation framework for evaluating language model's chess ability. Experimental results validate our model and dataset's effectiveness. We open source our code, model, and dataset at https://github.com/waterhorse1/ChessGPT.

Differentiable optimization algorithms often involve expensive computations of various meta-gradients. To address this, we design and implement TorchOpt, a new PyTorch-based differentiable optimization library. TorchOpt provides an expressive and unified programming interface that simplifies the implementation of explicit, implicit, and zero-order gradients. Moreover, TorchOpt has a distributed execution runtime capable of parallelizing diverse operations linked to differentiable optimization tasks across CPU and GPU devices. Experimental results demonstrate that TorchOpt achieves a 5.2× training time speedup in a cluster. TorchOpt is open-sourced at https://github.com/metaopt/torchopt and has become a PyTorch Ecosystem project.

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations. In this paper, we develop a unified framework that describes variations of GMRL algorithms and points out that existing stochastic meta-gradient estimators adopted by GMRL are actually \textbf{biased}. Such meta-gradient bias comes from two sources: 1) the compositional bias incurred by the two-level problem structure, which has an upper bound of $\mathcal{O}\big(K\alpha^{K}\hat{\sigma}_{\text{In}}|\tau|^{-0.5}\big)$ \emph{w.r.t.} inner-loop update step $K$, learning rate $\alpha$, estimate variance $\hat{\sigma}^{2}_{\text{In}}$ and sample size $|\tau|$, and 2) the multi-step Hessian estimation bias $\hat{\Delta}_{H}$ due to the use of autodiff, which has a polynomial impact $\mathcal{O}\big((K-1)(\hat{\Delta}_{H})^{K-1}\big)$ on the meta-gradient bias. We study tabular MDPs empirically and offer quantitative evidence that testifies our theoretical findings on existing stochastic meta-gradient estimators. Furthermore, we conduct experiments on Iterated Prisoner's Dilemma and Atari games to show how other methods such as off-policy learning and low-bias estimator can help fix the gradient bias for GMRL algorithms in general.

Achieving human-level dexterity is an important open problem in robotics. However, tasks of dexterous hand manipulation even at the baby level are challenging to solve through reinforcement learning (RL). The difficulty lies in the high degrees of freedom and the required cooperation among heterogeneous agents (e.g., joints of fingers). In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects. Tasks in Bi-DexHands are first designed to match human-level motor skills according to literature in cognitive science, and then are built in Issac Gym; this enables highly efficient RL trainings, reaching 30,000+ FPS by only one single NVIDIA RTX 3090. We provide a comprehensive benchmark for popular RL algorithms under different settings; this includes multi-agent RL, offline RL, multi-task RL, and meta RL. Our results show that PPO type on-policy algorithms can learn to solve simple manipulation tasks that are equivalent up to 48-month human baby (e.g., catching a flying object, opening a bottle), while multi-agent RL can further help to learn manipulations that require skilled bimanual cooperation (e.g., lifting a pot, stacking blocks). Despite the success on each individual task, when it comes to mastering multiple manipulation skills, existing RL algorithms fail to work in most of the multi-task and the few-shot learning tasks, which calls for more future development from the RL community. Our project is open-sourced at https://github.com/PKU-MARL/DexterousHands.

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed the task-specific information contained in prior trajectories? 2. How to collect informative trajectories of which the corresponding context reflects the specification of tasks? To this end, we propose a novel Meta-RL framework called CCM (Contrastive learning augmented Context-based Meta-RL). We first focus on the contrastive nature behind different tasks and leverage it to train a compact and sufficient context encoder. Further, we train a separate exploration policy and theoretically derive a new information-gain-based objective which aims to collect informative trajectories in a few steps. Empirically, we evaluate our approaches on common benchmarks as well as several complex sparse-reward environments. The experimental results show that CCM outperforms state-of-the-art algorithms by addressing previously mentioned problems respectively.

Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient. Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples. Though with significant performance improvement, it commonly suffers from two critical issues: the non-compatibility with mainstream industrial deployment and the heavy computational burdens, both due to the inner-loop gradient operation. These two issues make them hard to be applied in practical recommender systems. To enjoy the benefits of meta learning framework and mitigate these problems, we propose a recommendation framework called Contextual Modulation Meta Learning (CMML). CMML is composed of fully feed-forward operations so it is computationally efficient and completely compatible with the mainstream industrial deployment. CMML consists of three components, including a context encoder that can generate context embedding to represent a specific task, a hybrid context generator that aggregates specific user-item features with task-level context, and a contextual modulation network, which can modulate the recommendation model to adapt effectively. We validate our approach on both scenario-specific and user-specific cold-start setting on various real-world datasets, showing CMML can achieve comparable or even better performance with gradient based methods yet with higher computational efficiency and better interpretability.

When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population. Within such a process, the update rules of "who to compete with" (i.e., the opponent mixture) and "how to beat them" (i.e., finding best responses) are underpinned by manually developed game theoretical principles such as fictitious play and Double Oracle. In this paper, we introduce a novel framework—Neural Auto-Curricula (NAC)—that leverages meta-gradient descent to automate the discovery of the learning update rule without explicit human design. Specifically, we parameterise the opponent selection module by neural networks and the best-response module by optimisation subroutines, and update their parameters solely via interaction with the game engine, where both players aim to minimise their exploitability. Surprisingly, even without human design, the discovered MARL algorithms achieve competitive or even better performance with the state-of-the-art population-based game solvers (e.g., PSRO) on Games of Skill, differentiable Lotto, non-transitive Mixture Games, Iterated Matching Pennies, and Kuhn Poker. Additionally, we show that NAC is able to generalise from small games to large games, for example training on Kuhn Poker and outperforming PSRO on Leduc Poker. Our work inspires a promising future direction to discover general MARL algorithms solely from data.

Compressed sensing magnetic resonance imaging (CS-MRI) is a technique aimed at accelerating the data acquisition of MRI. While down-sampling in k-space proportionally reduces the data acquisition time, it results in images corrupted by aliasing artifacts and blur. To reconstruct images from the down-sampled k-space, recent deep-learning based methods have shown better performance compared with classical optimization-based CS-MRI methods. However, they usually use deep neural networks as a black-box, which directly maps the corrupted images to the target images from fully-sampled k-space data. This lack of transparency may impede practical usage of such methods. In this work, we propose a deep reinforcement learning based method to reconstruct the corrupted images with meaningful pixel-wise operations (e.g. edge enhancing filters), so that the reconstruction process is transparent to users. Specifically, MRI reconstruction is formulated as Markov Decision Process with discrete actions and continuous action parameters. We conduct experiments on MICCAI dataset of brain tissues and fastMRI dataset of knee images. Our proposed method performs favorably against previous approaches. Our trained model learns to select pixel-wise operations that correspond to the anatomical structures in the MR images. This makes the reconstruction process more interpretable, which would be helpful for further medical analysis.