Searcharxiv⌕ Search

arXiv subjects

Sergey Levine

Publications and source records attributed to Sergey Levine.

At least 19 recordsLinked to original sources
arXiv2026

Stabilizing On-Policy Targeted Guidance in Agentic Reinforcement Learning

Naive on-policy RL is often bottlenecked by the capabilities of the base model --- insufficient coverage can result in an inability to learn from certain rewards. At the same time, rewards in modern post-training systems often come from rich textual sources, e.g. judge models with a rubric of criteria. Can we utilize such structures to provide a rich directional signal that enables improving on otherwise difficult to optimize rewards? In this work, we examine a framework we refer to as targeted guidance that learns from per-turn textual feedback via an on-policy self-distillation objective. Our focus is not only on directly improving hard-to-optimize behaviors, but on how to do so throughout the training process without degrading baseline RL performance. Over a range of settings across an agentic multi-turn software engineering environment, we find success by combining targeted self-distillation with a per-criteria RL reward, and by limiting feedback to turns where the policy specifically fails. We further examine the design choices that lead to stable entropy and reduce oscillatory behavior throughout training.

cs.LG↗
arXiv2026

GSBR: Geometric Support Behavior Regularization for Online RL

Regularizing online reinforcement learning (RL) toward a pretrained base policy can improve sample efficiency and learning stability, but regularization that is too restrictive limits how much the policy can improve. Base policies -- typically diffusion or flow-matching models trained by imitation learning on large, diverse datasets -- capture many behaviors that are reasonable but suboptimal. Existing regularizers using such base policies are too restrictive in one of two ways: behavioral cloning regularizers pull the actor toward the full base-policy distribution, penalizing it for discarding suboptimal modes, while hard support constraints forbid improvements that lie just outside the base policy's support. We propose Geometric Support Behavior Regularization (GSBR), which penalizes actions by their distance from the base policy's support. Actions within the support incur no penalty, so the actor can concentrate on high-value modes; outside the support, where value estimates are less reliable, the penalty grows smoothly with distance while still permitting improvement when the value gained outweighs the penalty. GSBR estimates this distance from a finite set of base-policy samples, so it requires only sample access to the base policy. Across 19 tasks on four robotic benchmarks, GSBR raises the average success rate from 33% for the base policy to 95%, achieving the highest average success rate and throughput among all compared methods, with about 23% higher normalized throughput than the next-best RL method. Project website and open-source code at https://charlesxu0124.github.io/gsbr/ .

cs.RO↗
arXiv2026

Offline Materials Optimization with CliqueFlowmer

Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling methods are ineffective at boldly exploring attractive regions of the materials space due to their maximum likelihood training. In this work, we offer an alternative CMD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. To that end, we introduce a domain-specific model, dubbed CliqueFlowmer, that incorporates recent advances of clique-based MBO into transformer and flow generation. We validate this model's optimization abilities and show that materials it produces strongly outperform those from generative baselines. To support specialized materials discovery applications and broader interdisciplinary research, we release our code (https://github.com/znowu/CliqueFlowmer), model weights (https://huggingface.co/iamkuba/CliqueFlowmer), and an interactive demo (https://cliqueflowmer.znowu.workers.dev).

cs.AI↗
arXiv2026

Value Forcing: Aligning Return Distributions at All Noise Levels

Learning accurate value functions is central to reinforcement learning (RL), yet remains challenging because supervision is limited and indirect: ground-truth values are unavailable, and each transition in the data only provides an immediate reward that can be used to construct bootstrapped targets as supervision. This challenge is particularly pronounced when data is limited or reward signals are sparse, as is common in real-world applications such as robotics. We argue that the key to accurate value learning in this limited data regime is extracting richer learning signals from the available data. In this paper, we introduce Value Forcing, a new approach that uses flow matching to estimate return distributions and enables accurate value learning from limited data. Our key insight is that we can extract richer learning signals by enforcing Bellman consistency at every noise level. Empirically, Value Forcing improves the accuracy of estimating the return distribution, and prevents the distribution from collapsing to a single value, as occurs with prior methods. We instantiate Value Forcing with two practical value-learning algorithms: VF, an actor-critic method, and IVF, an implicit value-learning method. We evaluate both algorithms across $26$ long-horizon tasks in the offline RL setting and find that they outperform prior value-learning methods, with particularly large gains when data is limited. Our project website is available at https://chongyi-zheng.github.io/value-forcing.

cs.LG↗
arXiv2026

Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-use, web browsing, and dialogue with people. In the absence of expert demonstrations, training LLM agents has relied on policy gradient methods that optimize LLM policies with respect to an (often sparse) reward function. However, in long-horizon tasks with sparse rewards, learning from trajectory-level rewards can be noisy, leading to training that is unstable and has high sample complexity. Furthermore, policy improvement hinges on discovering better actions through exploration, which can be difficult when actions lie in natural language space. In this paper, we propose Natural Language Actor-Critic (NLAC), a novel actor-critic algorithm that trains LLM policies using a generative LLM critic that produces natural language rather than scalar values. This approach leverages the inherent strengths of LLMs to provide a richer and more actionable training signal; particularly, in tasks with large, open-ended action spaces, natural language explanations for why an action is suboptimal can be immensely useful for LLM policies to reason how to improve their actions, without relying on random exploration. Furthermore, our approach can be trained off-policy without policy gradients, offering a more data-efficient and stable alternative to existing on-policy methods. We present results on a mixture of reasoning, web browsing, and tool-use with dialogue tasks, demonstrating that NLAC shows promise in outperforming existing training approaches and offers a more scalable and stable training paradigm for LLM agents.

cs.LG↗
arXiv2026

Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment

A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are commonly modeled using simulators, which impose computational approximations. Meanwhile, experimental measurements more faithfully represent the real world, but experimental data typically consists of observations that only partially reflect the system's full underlying state. We propose a data-driven distribution alignment framework that bridges this simulation-to-experiment gap by pre-training a generative model on fully observed (but imperfect) simulation data, then aligning it with partial (but real) observations of experimental data. While our method is domain-agnostic, we ground our approach in the physical sciences by introducing Adversarial Distribution Alignment (ADA). This method aligns a generative model of atomic positions -- initially trained on a simulated Boltzmann distribution -- with the distribution of experimental observations. We prove that our method recovers the target observable distribution, even with multiple, potentially correlated observables. We also empirically validate our framework on synthetic, molecular, and experimental protein data, demonstrating that it can align generative models with diverse observables. Our code is available at https://kaityrusnelson.com/ada/.

cs.LG↗
arXiv2026

Robotic Data Inoculation

Modern robot learning systems feed on high-quality demonstration data, and their performance hinges on coverage. Without good coverage, small errors compound and the policy can quickly go into out-of-distribution states from which it cannot recover. Yet there is no principled way of collecting high-coverage data, and data collection often relies on heuristic instructions to human operators. Purely online reinforcement learning (RL) explores at the cost of safety and sample efficiency, while DAgger-style interventions require the policy to fail by chance before a human can correct it. In this paper, we ask instead whether we can modify how the robot behaves during data collection to collect more useful data. We propose Data Inoculation (DI), a shared-control framework in which a human provide closed-loop teleoperation commands while a residual policy perturbs these commands. The residual policy is trained online, on the growing dataset, with the same reward-maximizing objective later used for policy extraction, so its perturbations steer data collection toward the deviations a policy trained on the data would make. These perturbations expose the robot to a wider range of states, while the human's continuous corrections provide recovery demonstrations, "inoculating" the dataset against the learner's future mistakes while the human remains in control. On three challenging real-world robotic tasks, DI consistently improves or matches the success rate of policies trained with both behavioral cloning and offline RL, showing DI as an effective data collection strategy for improving downstream policy performance.

cs.RO↗
arXiv2026

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

cs.LG↗
arXiv2026

Reinforcement Learning via Advantage Guidance

Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems suffer from instability and hyperparameter sensitivity. In contrast, supervised learning provides a stable and scalable training objective, but is fundamentally limited by the quality of the demonstrated behavior. In this paper, we ask whether we can perform policy optimization with something as simple and stable as supervised learning but as performant as RL. Unfortunately, naively training the policy with supervised learning and conditioning on future rewards or advantages typically underperform dedicated RL methods. We introduce a new policy extraction method, Advantage Guidance, that retains the simple supervised learning structure with advantage conditioning while outperforming prior RL methods through effective conditional training and contrastive diffusion guidance during sampling. We show that Advantage Guidance can significantly improve a model's ability to respond to conditional advantage signals, and the contrastive guidance during sampling can use the learned advantage-conditioned policy to target the KL-regularized optimal policy. Empirically, we find that Advantage Guidance significantly outperforms prior state-of-the-art RL methods on 26 long-horizon, sparse reward tasks across datasets with varying degrees of optimality.

cs.LG↗
arXiv2026

Measuring Empowerment from Offline Data for Intrinsically Motivated Exploration

Large, unlabeled datasets of prior experience have become increasingly available for agentic tasks in domains such as robotics and coding. A common recipe for these tasks is to train a policy using the prior data, and then further improve it with online rollouts. But while much work has studied how to use both the offline and online data for policy extraction, far less work has been done to understand how the prior data can be used to efficiently \textit{explore} during the online learning phase. Previous work has attempted to formalize this idea by defining the \textit{empowerment}, a measure of how many future states an agent can realize; states with higher empowerment require more exploration as there are more futures to explore. However, existing methods for estimating empowerment require online policy rollouts in the environment. We propose the first method for estimating empowerment from unlabeled prior data, without any environment interaction. By jointly learning an empowerment-maximizing policy together with its discounted state-occupancy measure, our estimator can be trained on unlabeled trajectories generated from any unknown policy. We demonstrate that our empowerment estimator qualitatively gives intuitive empowerment measures and show that the pretrained estimator can be used to improve exploration in the online goal-conditioned reinforcement learning setting. Code is available at \url{https://github.com/ishirgarg/offline-empowerment}.

cs.LG↗
arXiv2026

Scaling Online Optimal Transport Minibatches for Flow Matching

A central challenge in scaling flow models is maintaining stability in training and integration. In flow matching, this stability depends critically on how source samples are paired with data. Independent random pairing introduces substantial stochasticity, motivating minibatch optimal transport (OT) to construct online source-target couplings that reduce this randomness (Tong et al., 2024). However, as applications extend to larger and higher-dimensional datasets, small minibatches can limit these benefits, while scaling the coupling to substantially larger minibatches at every iteration is computationally prohibitive. Moreover, how OT coupling affects the full stochastic gradient and integration remains theoretically unresolved. In this work, we develop a scalable online entropic OT approximation that enables substantially larger source-target couplings while preserving the benefits of OT. We close the theoretical gap for both unregularized and entropic OT by proving strict reductions in full stochastic-gradient variance and integration error relative to independent pairing, and further characterize how these improvements strengthen as the online coupling minibatch grows. Experiments on single-cell gene interpolation-flow and image-flow training validate these predictions, showing that larger online couplings consistently improve training stability and final generation performance.

cs.LG↗
arXiv2026

Scaling Empowered Agents

Empowerment measures the capacity of an agent to actively control its environment. In this work, we explain the connection between skill learning and empowerment. While skill learning is not empowerment, we introduce a simple scalable recipe for empowerment maximization: empowerment corresponds to the number of executable skills from a state, so maximizing empowerment corresponds to reaching states that are good starting points for many skills. Our recipe applies to arbitrary underlying skill learning methods. Whereas most prior work on empowerment looks at tabular settings, this recipe enables us to study empowerment at a scale where we can realize theoretically-predicted but empirically-elusive properties of empowerment (e.g., gathering resources, environment modification, survival). Experiments show that empowerment maximization unlocks interesting emergent properties, such as building a house in Crafter. Website and code at \href{https://empowerment-geometry.github.io/scaling-empowerment/}{this https url}.

cs.AI↗
arXiv2026

The Geometry of Empowerment

Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connection between empowerment and structurally central states that provide broad access to future outcomes has remained an open question. In this work, we link empowerment maximization and skill-learning methods to provide new geometries for interpreting and analyzing empowerment. Our analyses answer longstanding open questions on the connections between empowerment and structural centrality. Our analyses also reveal distinctions between information and reward geometries, highlighting important theoretical implications to build scalable empowerment-maximization methods. Website and code can be found at https://empowerment-geometry.github.io/.

cs.LG↗
arXiv2026

Behavioral Cloning Mystery

Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking. Unfortunately, properly studying these anecdotal phenomena ("behavioral cloning mysteries") is challenging: in the real world, datasets and experiments are costly and not fully controllable; in simulation with synthetic data, these phenomena are often not easily observed partly due to the discrepancy between scripted policies and human demonstrations. In this work, we propose OCBench, a robotic manipulation benchmark with controllable scripted policies that have similar properties to human demonstrations. We show that, by mimicking key properties of human demonstrations, OCBench reproduces many anecdotal BC-related phenomena in controlled settings. With its GPU-accelerated environments and scripted policies, we demonstrate how OCBench enables scientific studies of previously reported BC-related phenomena by analyzing and refuting various hypotheses. Project page: https://seohong.me/projects/ocbench

cs.RO↗
arXiv2026

Leveraging Discrete Function Decomposability for Scientific Design

In the era of AI-driven science and engineering, we often want to design discrete objects in silico according to user-specified properties. For example, we may wish to design a protein to bind its target, arrange components within a circuit to minimize latency, or find materials with certain properties. Given a property predictive model, in silico design typically involves training a generative model over the design space (e.g., protein sequence space) to concentrate on designs with the desired properties. Distributional optimization$\unicode{x2013}$which can be formalized as an estimation of distribution algorithm or as reinforcement learning policy optimization$\unicode{x2013}$finds the generative model that maximizes an objective function in expectation. Optimizing a distribution over discrete-valued designs is in general challenging because of the combinatorial nature of the design space. However, many property predictors in scientific applications are decomposable in the sense that they can be factorized over design variables in a way that could in principle enable more effective optimization. For example, amino acids at a catalytic site of a protein may only loosely interact with amino acids of the rest of the protein to achieve maximal catalytic activity. Current distributional optimization algorithms are unable to make use of such decomposability structure. Herein, we propose and demonstrate use of a new distributional optimization algorithm, Decomposition-Aware Distributional Optimization (DADO), that can leverage any decomposability defined by a junction tree on the design variables, to make optimization more efficient. At its core, DADO employs a soft-factorized "search distribution"$\unicode{x2013}$a learned generative model$\unicode{x2013}$for efficient navigation of the search space, invoking graph message-passing to coordinate optimization across linked factors.

cs.LG↗
arXiv2026

Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching

Current paradigms for training language models via reinforcement learning rely heavily on sparse outcome rewards. However, as we pursue tasks that require longer and more complicated trajectories, such strategies result in slow learning. Prior work has attempted to address this problem by rewarding partial progress; however, naive formulations are often biased and converge to suboptimal policies. We show that a simple and unbiased dense reward formulation, which we term progressive point matching, scales exponentially more efficiently to long-horizon tasks by rewarding partial progress on a segment level, both theoretically and empirically via synthetic environments. We then show how progressive point matching can be practically instantiated using a single reference trajectory per task. On extremely hard math reasoning problems, sparse outcome rewards cannot make any progress, whereas segment-level rewards enable improvements at larger test-time token budgets when measured by success rate or pass@k.

cs.LG↗
arXiv2026

Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency

While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist policies, such as VLAs, poses a fundamental obstacle to effective RL improvement. In particular, their severe inference latency---which can lead to pauses or jerky movements---can alter the effective environment dynamics and, if not correctly accounted for, break the Markov assumption that RL relies on, causing standard RL algorithms to fail completely. In this work, we introduce a latency-aware framework, Asynchronous RL with Intermediate Information (ARLI), that enables RL-based improvement of generalist policies under inference delays. Our framework builds on asynchronous inference approaches, which interleave action generation with execution to hide latency, and addresses its incompatibility with RL by providing a low-latency RL policy design that maximizes reactivity within the inference window through two contributions: state augmentations that restore near-Markovian structure by incorporating committed actions and a mid-inference observation. We evaluate our approach across simulated and real-world manipulation tasks, and find that it enables effective finetuning under inference delays where standard RL fails entirely, even matching or exceeding the performance of standard RL in idealized no-latency settings.

cs.RO↗
arXiv2026

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. The inference-time solution, Verbalized Sampling, broadens the simulator's behavior by sampling from a verbalized response distribution, reducing mode collapse. The training-time solution, Co-Training, jointly optimizes the policy against a population of trainable simulators, preventing it from overfitting to any single simulator's mode. We validate both solutions on three multi-turn benchmarks: Persuasion for Good, $τ^2$-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions preserve the policy diversity that collapses under single-simulator RL. To support further work in this direction, we release SCOPE, an open-source framework for Population Co-Training multi-agent RL. More broadly, our results suggest that the diversity of the training environment, not only the policy, is critical to the generalization of multi-turn RL to real-world deployment.

cs.CL↗