Chongyi Zheng

Homer Walke, Kevin Black, Abraham Lee et al. · berkeley, stanford

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research on scalable robot learning. BridgeData V2 contains 60,096 trajectories collected across 24 environments on a publicly available low-cost robot. BridgeData V2 provides extensive task and environment variability, leading to skills that can generalize across environments, domains, and institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments, we train 6 state-of-the-art imitation learning and offline reinforcement learning methods on our dataset, and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models, and that training on a greater variety of skills leads to improved generalization. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods. Project page at https://rail-berkeley.github.io/bridgedata

Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the future. While prior methods have used contrastive predictive coding to model time series data, learning representations that encode long-term dependencies usually requires large amounts of data. In this paper, we introduce a temporal difference version of contrastive predictive coding that stitches together pieces of different time series data to decrease the amount of data required to learn predictions of future events. We apply this representation learning method to derive an off-policy algorithm for goal-conditioned RL. Experiments demonstrate that, compared with prior RL methods, ours achieves $2 \times$ median improvement in success rates and can better cope with stochastic environments. In tabular settings, we show that our method is about $20 \times$ more sample efficient than the successor representation and $1500 \times$ more sample efficient than the standard (Monte Carlo) version of contrastive predictive coding.

Chongyi Zheng, Benjamin Eysenbach, Homer Walke et al.

Robotic systems that rely primarily on self-supervised learning have the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. In the same way that prior robotic systems have leveraged self-supervised techniques from computer vision (CV) and natural language processing (NLP), our work builds on prior work showing that the reinforcement learning (RL) itself can be cast as a self-supervised problem: learning to reach any goal without human-specified rewards or labels. Despite the seeming appeal, little (if any) prior work has demonstrated how self-supervised RL methods can be practically deployed on robotic systems. By first studying a challenging simulated version of this task, we discover design decisions about architectures and hyperparameters that increase the success rate by $2 \times$. These findings lay the groundwork for our main result: we demonstrate that a self-supervised RL algorithm based on contrastive learning can solve real-world, image-based robotic manipulation tasks, with tasks being specified by a single goal image provided after training.

Ruihan Yang, Zhuoqun Chen, Jianhan Ma et al.

The agility of animals, particularly in complex activities such as running, turning, jumping, and backflipping, stands as an exemplar for robotic system design. Transferring this suite of behaviors to legged robotic systems introduces essential inquiries: How can a robot learn multiple locomotion behaviors simultaneously? How can the robot execute these tasks with a smooth transition? How to integrate these skills for wide-range applications? This paper introduces the Versatile Instructable Motion prior (VIM) - a Reinforcement Learning framework designed to incorporate a range of agile locomotion tasks suitable for advanced robotic applications. Our framework enables legged robots to learn diverse agile low-level skills by imitating animal motions and manually designed motions. Our Functionality reward guides the robot's ability to adopt varied skills, and our Stylization reward ensures that robot motions align with reference motions. Our evaluations of the VIM framework span both simulation and the real world. Our framework allows a robot to concurrently learn diverse agile locomotion skills using a single learning-based controller in the real world. Videos can be found on our website: https://rchalyang.github.io/VIM/

Aravind Venugopal, Jiayu Chen, Xudong Wu et al.

The temporal lag between actions and their long-term consequences makes credit assignment a challenge when learning goal-directed behaviors from data. Generative world models capture the distribution of future states an agent may visit, indicating that they have captured temporal information. How can that temporal information be extracted to perform credit assignment? In this paper, we formalize how the temporal information stored in world models encodes the underlying geometry of the world. Leveraging optimal transport, we extract this geometry from a learned model of the occupancy measure into a reward function that captures goal-reaching information. Our resulting method, Occupancy Reward Shaping, largely mitigates the problem of credit assignment in sparse reward settings. ORS provably does not alter the optimal policy, yet empirically improves performance by 2.2x across 13 diverse long-horizon locomotion and manipulation tasks. Moreover, we demonstrate the effectiveness of ORS in the real world for controlling nuclear fusion on 3 Tokamak control tasks. Code: https://github.com/aravindvenu7/occupancy_reward_shaping; Website: https://aravindvenu7.github.io/website/ors/

Chongyi Zheng, Seohong Park, Sergey Levine et al.

Large-scale pre-training has fundamentally changed how machine learning research is done today: large foundation models are trained once, and then can be used by anyone in the community (including those without data or compute resources to train a model from scratch) to adapt and fine-tune to specific tasks. Applying this same framework to reinforcement learning (RL) is appealing because it offers compelling avenues for addressing core challenges in RL, including sample efficiency and robustness. However, there remains a fundamental challenge to pre-train large models in the context of RL: actions have long-term dependencies, so training a foundation model that reasons across time is important. Recent advances in generative AI have provided new tools for modeling highly complex distributions. In this paper, we build a probabilistic model to predict which states an agent will visit in the temporally distant future (i.e., an occupancy measure) using flow matching. As large datasets are often constructed by many distinct users performing distinct tasks, we include in our model a latent variable capturing the user intention. This intention increases the expressivity of our model, and enables adaptation with generalized policy improvement. We call our proposed method intention-conditioned flow occupancy models (InFOM). Comparing with alternative methods for pre-training, our experiments on $36$ state-based and $4$ image-based benchmark tasks demonstrate that the proposed method achieves $1.8 \times$ median improvement in returns and increases success rates by $36\%$. Website: https://chongyi-zheng.github.io/infom Code: https://github.com/chongyi-zheng/infom

Perry Dong, Chongyi Zheng, Chelsea Finn et al.

While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to provide stronger learning signals and to enable applications in exploration and safe RL. While the predominant method for estimating the return distribution is by modeling it as a categorical distribution over discrete bins or estimating a finite number of quantiles, such approaches leave unanswered questions about the fine-grained structure of the return distribution and about how to distinguish states with high return uncertainty for decision-making. The key idea in this paper is to use modern, flexible flow-based models to estimate the full future return distributions and identify those states with high return variance. We do so by formulating a new flow-matching objective that generates probability density paths satisfying the distributional Bellman equation. Building upon the learned flow models, we estimate the return uncertainty of distinct states using a new flow derivative ODE. We additionally use this uncertainty information to prioritize learning a more accurate return estimation on certain transitions. We compare our method (Value Flows) with prior methods in the offline and online-to-online settings. Experiments on $37$ state-based and $25$ image-based benchmark tasks demonstrate that Value Flows achieves a $1.3\times$ improvement on average in success rates. Website: https://pd-perry.github.io/value-flows Code: https://github.com/chongyi-zheng/value-flows

Devan Shah, Owen Yang, Daniel Yang et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and programming tasks, but standard approaches that optimize single-attempt accuracy can inadvertently suppress response diversity across repeated attempts, narrowing exploration and overlooking underrepresented strategies. We introduce UpSkill, a training time method that adapts Mutual Information Skill Learning (MISL) to LLMs for optimizing pass@k correctness. We propose a novel reward that we implement within Group Relative Policy Optimization (GRPO): a token-level mutual information (MI) reward that encourages trajectory specificity to z. Experiments on GSM8K with three open-weight models, Llama 3.1-8B, Qwen 2.5-7B, and R1-Distilled-Qwen2.5-Math-1.5B, show that UpSkill improves multi-attempt metrics on the stronger base models, yielding mean gains of ~3% in pass@k for both Qwen and Llama without degrading pass@1. Additionally, we find both empirical and theoretical evidence that improvements in pass@k are closely tied to the mutual information objective.

Chongyi Zheng, Jens Tuyls, Joanne Peng et al.

Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively argued that moving away from mutual information and instead optimizing a certain Wasserstein distance is important for good performance. In this paper, we argue that the benefits seen in that paper can largely be explained within the existing framework of mutual information skill learning (MISL). Our analysis suggests a new MISL method (contrastive successor features) that retains the excellent performance of METRA with fewer moving parts, and highlights connections between skill learning, contrastive representation learning, and successor features. Finally, through careful ablation studies, we provide further insight into some of the key ingredients for both our method and METRA.

Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin Eysenbach

As machine learning has moved towards leveraging large models as priors for downstream tasks, the community has debated the right form of prior for solving reinforcement learning (RL) problems. If one were to try to prefetch as much computation as possible, they would attempt to learn a prior over the policies for some yet-to-be-determined reward function. Recent work (forward-backward (FB) representation learning) has tried this, arguing that an unsupervised representation learning procedure can enable optimal control over arbitrary rewards without further fine-tuning. However, FB's training objective and learning behavior remain mysterious. In this paper, we demystify FB by clarifying when such representations can exist, what its objective optimizes, and how it converges in practice. We draw connections with rank matching, fitted Q-evaluation, and contraction mapping. Our analysis suggests a simplified unsupervised pre-training method for RL that, instead of enabling optimal control, performs one step of policy improvement. We call our proposed method $\textbf{one-step forward-backward representation learning (one-step FB)}$. Experiments in didactic settings, as well as in $10$ state-based and image-based continuous control domains, demonstrate that one-step FB converges to errors $10^5$ smaller and improves zero-shot performance by $+24\%$ on average. Our project website is available at https://chongyi-zheng.github.io/onestep-fb.

Kathryn Wantlin, Chongyi Zheng, Benjamin Eysenbach

In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to quickly adapt to new tasks? A prerequisite for embodied agents deployed in real world interactions ought to be training with interaction, yet today's most successful AI models (e.g., VLMs, LLMs) are trained without an explicit notion of action. The problem of pure exploration (which assumes no data as input) is well studied in the reinforcement learning literature and provides agents with a wide array of experiences, yet it fails to prepare them for rapid adaptation to new tasks. Today's language and vision models are trained on data provided by humans, which provides a strong inductive bias for the sorts of tasks that the model will have to solve (e.g., modeling chords in a song, phrases in a sonnet, sentences in a medical record). However, when they are prompted to solve a new task, there is a faulty tacit assumption that humans spend most of their time in the most rewarding states. The key contribution of our paper is a method for pre-training interactive agents in a self-supervised fashion, so that they can instantly mimic human demonstrations. Our method treats goals (i.e., observations) as the atomic construct. During training, our method automatically proposes goals and practices reaching them, building off prior work in reinforcement learning exploration. During evaluation, our method solves an (amortized) inverse reinforcement learning problem to explain demonstrations as optimal goal-reaching behavior. Experiments on standard benchmarks (not designed for goal-reaching) show that our approach outperforms prior methods for zero-shot imitation.

Vivek Myers, Chongyi Zheng, Anca Dragan et al.

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor features learned by contrastive learning (after a change of variables) form a temporal distance that does satisfy the triangle inequality, even in stochastic settings. Importantly, this temporal distance is computationally efficient to estimate, even in high-dimensional and stochastic settings. Experiments in controlled settings and benchmark suites demonstrate that an RL algorithm based on these new temporal distances exhibits combinatorial generalization (i.e., "stitching") and can sometimes learn more quickly than prior methods, including those based on quasimetrics.

Beining Han, Chongyi Zheng, Harris Chan et al.

Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and unrelated to the underlying problem, such as background shifts for visual input agents. Unfortunately, deep RL policies are usually sensitive to these changes and fail to act robustly against them. This resembles the problem of domain generalization in supervised learning. In this work, we study this problem for goal-conditioned RL agents. We propose a theoretical framework in the Block MDP setting that characterizes the generalizability of goal-conditioned policies to new environments. Under this framework, we develop a practical method PA-SkewFit that enhances domain generalization. The empirical evaluation shows that our goal-conditioned RL agent can perform well in various unseen test environments, improving by 50% over baselines.

Tonghan Wang, Jianhao Wang, Chongyi Zheng et al.

Reinforcement learning encounters major challenges in multi-agent settings, such as scalability and non-stationarity. Recently, value function factorization learning emerges as a promising way to address these challenges in collaborative multi-agent systems. However, existing methods have been focusing on learning fully decentralized value functions, which are not efficient for tasks requiring communication. To address this limitation, this paper presents a novel framework for learning nearly decomposable Q-functions (NDQ) via communication minimization, with which agents act on their own most of the time but occasionally send messages to other agents in order for effective coordination. This framework hybridizes value function factorization learning and communication learning by introducing two information-theoretic regularizers. These regularizers are maximizing mutual information between agents' action selection and communication messages while minimizing the entropy of messages between agents. We show how to optimize these regularizers in a way that is easily integrated with existing value function factorization methods such as QMIX. Finally, we demonstrate that, on the StarCraft unit micromanagement benchmark, our framework significantly outperforms baseline methods and allows us to cut off more than $80\%$ of communication without sacrificing the performance. The videos of our experiments are available at https://sites.google.com/view/ndq.