Policy Learning

Follow this topic Ask about this topic

Momentum

79 papers in the last four weeks, up 316% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 416

May 7, 2026cs.LG

Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its standard advantage weighted policy gradient suffers from three structural weaknesses, including high variance updates, vanishing gradients in zero-advantage regions, and exploration bottlenecks when corrective signals are insufficient. We therefore propose Asymmetric On-Policy Distillation (AOPD), which replaces ineffective negative reinforcement with localized divergence minimization in non-positive advantage regions while preserving positive reinforcement learning. Experiments on mathematical reasoning benchmarks show that AOPD consistently outperforms standard OPD, with average gains of 4.09 / 8.34 under strong / weak initialization, respectively. AOPD also maintains higher policy entropy during training and better capability retention during sequential tool-use adaptation.

Nan Jia, Haojin Yang, Xing Ma +6

Huazhong University of Science and Technology · Peking University · Meituan

RL for Language Model Reasoning Language Model Distillation Policy Gradient Methods On-Policy Distillation Teacher-Student Learning Policy Learning

May 7, 2026cs.LG

On Training in Imagination

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true environment during policy updates. We study this training paradigm by quantifying how errors in learned dynamics and reward models affect returns and policy optimization. First, we extend the analysis of Asadi et al. (2018) to MDPs with learned reward models, and derive the optimal sample allocation--the ratio of dynamics samples to reward samples that minimizes a bound on return error under power-law scaling assumptions. We identify lower Lipschitz constants of the learned dynamics, reward, and policy as a representation desideratum that tightens this bound, and we connect this perspective to the temporal-straightening objective of Wang et al. (2026). Second, we examine how policy optimization with REINFORCE tolerates noisy rewards, which are often cheaper to obtain. We show that zero-mean reward noise leaves the gradient estimator unbiased and adds at most a variance term that decreases with the number of rollouts. This introduces a practical tradeoff: given a fixed budget, should one buy more rollouts with cheaper but noisier rewards, or fewer rollouts with more expensive but less noisy rewards? We reduce this choice to a one-dimensional optimization problem and characterize the optimum.

Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum +2

Weizmann Institute of Science · New York University · Columbia University

Reward Modeling Reinforcement Learning Policy Gradient Methods Policy Learning Model-Based RL

May 7, 2026cs.AI

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and distills new skills from experience. Existing methods optimize these capabilities in isolation or with separate reward sources, resulting in partial and conflicting evolution. We propose Skill1, a framework that trains a single policy to co-evolve skill selection, utilization, and distillation toward a shared task-outcome objective. The policy generates a query to search the skill library, re-ranks candidates to select one, solves the task conditioned on it, and distills a new skill from the trajectory. All learning derives from a single task-outcome signal. Its low-frequency trend credits selection and its high-frequency variation credits distillation. Experiments on ALFWorld and WebShop show that Skill1 outperforms prior skill-based and reinforcement learning baselines. Training dynamics confirm the co-evolution of the three capabilities, and ablations show that removing any credit signal degrades the evolution.

Yaorui Shi, Yuxin Chen, Zhengxi Lu +6

University of Science and Technology of China · 2Meituan · 3National University of Singapore +2

LLM Agent Skill Learning LLM Agent Skill Retrieval Policy Learning RL for LLM Agents Memory-Augmented Language Model Agents

May 7, 2026cs.CL

Milestone-Guided Policy Learning for Long-Horizon Language Agents

While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution, where correct early actions are penalized due to terminal failures, and sample inefficiency, where scarce successful trajectories result in near-total loss of learning signal. We introduce a milestone-guided policy learning framework, BEACON, that leverages the compositional structure of long-horizon tasks to ensure precise credit assignment. BEACON partitions trajectories at milestone boundaries, applies temporal reward shaping within segments to credit partial progress, and estimates advantages at dual scales to prevent distant failures from corrupting the evaluation of local actions. On ALFWorld, WebShop, and ScienceWorld, BEACON consistently outperforms GRPO and GiGPO. Notably, on long-horizon ALFWorld tasks, BEACON achieves 92.9% success rate, nearly doubling GRPO's 53.5%, while improving effective sample utilization from 23.7% to 82.0%. These results establish milestone-anchored credit assignment as an effective paradigm for training long-horizon language agents. Code is available at https://github.com/ZJU-REAL/BEACON.

Zixuan Wang, Yuchen Yan, Hongxing Li +7

Zhejiang University · Baidu Inc.

Credit Assignment in RL Long-Horizon Agent Tasks Long-Horizon LLM Agents Policy Learning RL for LLM Agents

May 7, 2026stat.ML

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement

We investigate the ability of transformers to perform in-context reinforcement learning (ICRL), where a model must infer and execute learning algorithms from trajectory data without parameter updates. We show that a linear self-attention transformer block can provably implement policy-improvement methods, including semi-gradient SARSA and actor-critic, via explicit parameter constructions. Beyond existence, we design a teacher-mimicking training procedure, analyze its gradient-flow dynamics, and establish the first convergence guarantee in the ICRL literature: under suitable richness conditions on the training MDP distribution, gradient flow converges locally and exponentially to an optimal parameter manifold corresponding to the desired RL update. Empirically, training transformers on randomly generated tabular MDPs confirms these predictions: the learned models recover the parameter structure of our explicit constructions and, when deployed on unseen MDPs, deliver strong in-context control performance. Together, these results illuminate how transformer architectures internalize and execute classical reinforcement learning algorithms in context, bridging mechanistic understanding and training dynamics in ICRL.

Haodong Liang, Lifeng Lai

Department of Electrical and Computer Engineering, University of California, Davis

Reinforcement Learning Transformer-Based RL Policy Optimization In-Context RL Policy Learning

May 7, 2026cs.LG

Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning

Offline-to-online reinforcement learning with action chunking eliminates multi-step off-policy bias and enables temporally coherent exploration, but all existing methods use a fixed chunk size across every state. This is suboptimal: near contact events the agent needs short chunks for reactive control, while during free-space motion long chunks provide better credit assignment. The natural solution is to train critics for several chunk sizes and select the best one at each state, but naive comparison of learned critic values systematically collapses to the shortest chunk due to discount-scale mismatch, and degrades to noise in low-value states. We propose Adaptive Q-Chunking (AQC), which resolves both failures by comparing the advantage of each chunk size relative to a per-horizon baseline, normalized by the discount factor. This criterion converts biased wrong answers into unbiased near-random choices when no genuine signal exists, and becomes discriminative when a particular scale enables better planning. We prove theoretical bounds on the advantage selector's noise immunity and on the value dominance of adaptive chunking over any fixed chunk size. We demonstrate that AQC achieves state-of-the-art offline and online success rates on OGBench and Robomimic, and can be applied to enhance the performance of large-scale VLA models that predict action sequences, significantly boosting performance on RoboCasa-GR1 tasks.

Nandiraju Gireesh, Yuanliang Ju, He Wang

Peking University · Galbot · University of Toronto

Q-Learning Offline RL Action Chunking Policy Learning Offline-To-Online RL

May 6, 2026cs.LG

Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients

Active feature acquisition (AFA) considers prediction problems in which features are costly to obtain and the learner adaptively decides which feature values to acquire for each instance and when to stop and predict. AFA can be formulated as a partially observable Markov decision process (POMDP), which naturally admits a sequential decision-making perspective. In this paper, we present non-myopic pathwise policy gradients (NM-PPG), a new AFA method built around this formulation. We introduce a continuous relaxation of the acquisition process that enables pathwise gradients through the full acquisition trajectory, avoiding the high variance of standard score-function policy gradients while allowing end-to-end optimization of a non-myopic acquisition policy. To better align training with deployment, we further develop a straight-through rollout scheme that follows hard feature acquisitions in the forward pass while backpropagating through the corresponding soft relaxation in the backward pass. We stabilize optimization with entropy regularization and staged temperature sharpening. Experiments on both synthetic and real-world datasets demonstrate that NM-PPG yields superior performance relative to state-of-the-art AFA baselines.

Linus Aronsson, Morteza Haghir Chehreghani

Department of Computer Science and Engineering · Chalmers University of Technology & University of Gothenburg · Gothenburg, Sweden

Policy Gradient Active Learning Active Feature Acquisition Policy Gradient Methods Policy Learning

May 6, 2026cs.LG

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

Dillon Sandhu, Ronald Parr

Department of Computer Science, Duke University, USA

Policy Optimization Policy Iteration Proximal Policy Optimization Safe RL Policy Learning

May 6, 2026cs.AI

LANTERN: LLM-Augmented Neurosymbolic Transfer with Experience-Gated Reasoning Networks

Transfer learning in reinforcement learning (RL) seeks to accelerate learning in new tasks by leveraging knowledge from related sources. Existing neurosymbolic transfer methods, however, typically rely on manually specified task automata, assume a single source task, and use fixed knowledge-integration mechanisms that cannot adapt to varying source relevance. We propose LANTERN, a unified framework for multi-source neurosymbolic transfer that addresses these limitations through three components: (i) deterministic finite automata generated from natural language task descriptions using large language models, (ii) semantic embedding-based aggregation of multiple source policies weighted by cross-task similarity, and (iii) adaptive teacher-student gating based on temporal-difference error and semantic uncertainty. Across domains spanning resource management, navigation, and control, LANTERN achieves 40-60% improvements in sample efficiency over existing baselines while remaining robust to poorly aligned sources. These results demonstrate that multi-source, adaptively weighted neurosymbolic transfer can improve scalability and robustness in symbolic RL settings.

Mahyar Alinejad, Yue Wang, Amrit Singh Bedi +1

Department of Electrical and Computer Engineering, University of Central Florida, Orlando, Florida, USA · Department of Computer Science, University of Central Florida, Orlando, Florida, USA

Reinforcement Learning LLM-Guided RL Neurosymbolic Learning Policy Learning

May 6, 2026cs.LG

Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies

A key capability of intelligent agents is to act effectively under incomplete state observations. Recurrent policies address this by compressing observation histories into a hidden state. In this work, we show that the hidden state of a recurrent policy admits a control-theoretic interpretation: it plays the role of the co-state in Pontryagin's minimum principle, and the readout that maps it to actions implements control-Hamiltonian minimization. The hidden state thus tracks the gradient of the value function, encoding the optimality structure of the underlying control problem. We formalize this correspondence through a class of policies we refer to as co-state policies (CPs) and show that several modern recurrent cells implicitly realize this structure. The correspondence also allows for a co-state loss for actor-critic training, in which the critic's gradient serves as a target for the actor's hidden state. Empirically, we find that hidden states trained with the co-state loss encode co-state information beyond what is linearly decodable from the environment state alone, and that the loss improves policies both within and outside this class on challenging locomotion tasks, including the H1 and Berkeley humanoids. By connecting the minimum principle to recurrent memory, we provide a control-theoretic account of what hidden states compute in continuous control and a mechanism for shaping them toward optimality.

David Leeftink, Max Hinne, Marcel van Gerven

Department of Machine Learning and Neural Computating Donders Institute for Brain, Cognition and Behaviour Radboud University, Nijmegen, the Netherlands.

RL Control Reinforcement Learning Partially Observable RL Policy Learning Optimal Control

May 6, 2026cs.AI

On-line Learning in Tree MDPs by Treating Policies as Bandit Arms

A Tree Markov Decision Problem (T-MDP) is a finite-horizon MDP with a starting state

s_{1}

, in which every state is reachable from

s_{1}

through exactly one state-action trajectory. T-MDPs arise naturally as abstractions of decision making in sequential games with perfect recall, against stationary opponents. We consider the problem of on-line learning in T-MDPs, both in the PAC and the regret-minimisation regimes. We show that well-known bandit algorithms -- \textsc{Lucb} and \textsc{Ucb} -- can be applied on T-MDPs by treating each policy as an arm. The apparent technical challenge in this approach is that the number of policies is exponential in the number of states. Our main innovation is in the design of confidence bounds based on data shared by the policies, so that the bandit algorithms can yet be implemented with polynomial memory and per-step computation. We obtain instance-dependent upper bounds on sample complexity and regret that sum a ``gap term'' from every terminal state, rather than every policy. Empirically, our algorithms consistently outperform available alternatives on a suite of hidden-information games.

Anvay Shah, Ramsundar Anandanarayanan, Sharayu Moharir +1

Indian Institute of Technology Bombay · Mumbai, India

Markov Decision Processes Markov Models Interval Markov Decision Processes Policy Learning

May 6, 2026cs.LG

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability to learn new skills from new experiences diminishes over training. Recently, Mixture-of-Experts (MoE) networks have been reported to enable scaling laws and facilitate the learning of diverse skills. However, in continual reinforcement learning settings, their performance can degenerate as learning proceeds, indicating a loss of plasticity. To address this, building on Neural Tangent Kernel (NTK) theory, we formalize the plasticity loss in MoE policies as a loss of spectral plasticity. We then derive a tractable proxy for spectral plasticity, one expressible in terms of individual expert feature matrices. Leveraging this proxy, we introduce SPHERE, a practical Parseval penalty tailored for MoE-based policies that alleviates the loss of spectral plasticity. On MetaWorld and HumanoidBench, SPHERE improves average success under continual RL by 133% and 50% over an unregularized MoE baseline, while maintaining higher spectral plasticity throughout training.

Lirui Luo, Guoxi Zhang, Hongming Xu +2

State Key Lab of General AI, School of Intelligence Science and Technology, Peking University · State Key Laboratory of General Artificial Intelligence, BIGAI · Institute for Artificial Intelligence, Peking University

Loss of Plasticity Reinforcement Learning Mixture of Experts Neural Network Training Dynamics Policy Learning Continual RL

May 5, 2026cs.LG

Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies

We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies. By partitioning a distillation dataset of state action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%. Our results pave the path towards a more flexible form of distillation where both the decision boundary and surrogate models can be chosen within a margin of the original black box behavior.

Senne Deproost, Mehrdad Asadi, Ann Nowé

aVrije Universiteit Brussel · bFlanders Make

Reinforcement Learning Interpretability in RL Policy Learning

May 5, 2026cs.LG

Vanishing L2 regularization for the softmax Multi Armed Bandit

Multi Armed Bandit (MAB) algorithms are a cornerstone of reinforcement learning and have been studied both theoretically and numerically. One of the most commonly used implementation uses a softmax mapping to prescribe the optimal policy and served as the foundation for downstream algorithms, including REINFORCE. Distinct from vanilla approaches, we consider here the L2 regularized softmax policy gradient where a quadratic term is subtracted from the mean reward. Previous studies exploiting convexity failed to identify a suitable theoretical framework to analyze its convergence when the regularization parameter vanishes. We prove here theoretical convergence results and confirm empirically that this regime makes the L2 regularization numerically advantageous on standard benchmarks.

Stefana-Lucia Anita, Gabriel Turinici

CEREMADE, Universit´e Paris Dauphine - PSL, CNRS, Paris, France · ‘Octav Mayer” Institute of Mathematics of the Romanian Academy, Bd. Carol I 8, Ias¸i 700505, Romania

Multi-Armed Bandits Policy Gradient Policy Optimization Policy Gradient Methods Policy Learning

May 4, 2026cs.AI

T $^2$ PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T

^2

PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T

^2

PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T

^2

PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T

^2

PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at: https://github.com/WillDreamer/T2PO.

Haixin Wang, Hejie Cui, Chenwei Zhang +7

University of California, Los Angeles · 2Amazon.com Inc.

Agentic RL Reinforcement Learning RL Exploration Policy Learning RL for LLM Agents

May 3, 2026cs.LG

Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning

We propose Flow-Anchored Noise-conditioned Q-Learning (FAN), a highly efficient and high-performing offline reinforcement learning (RL) algorithm. Recent work has shown that expressive flow policies and distributional critics improve offline RL performance, but at a high computational cost. Specifically, flow policies require iterative sampling to produce a single action, and distributional critics require computation over multiple samples (e.g., quantiles) to estimate value. To address these inefficiencies while maintaining high performance, we introduce FAN. Our method employs a behavior regularization technique that uses a single flow policy iteration and requires a single Gaussian noise sample for distributional critics. Our theoretical analysis of convergence and performance bounds demonstrates that these simplifications not only improve efficiency but also lead to superior task performance. Experiments on robotic manipulation and locomotion tasks demonstrate that FAN achieves state-of-the-art performance while significantly reducing both training and inference runtimes. We release our code at https://github.com/brianlsy98/FAN.

Sungyoung Lee, Dohyeong Kim, Eshan Balachandar +2

The University of Texas at Austin, Austin, TX, USA · Independent Researcher, Seoul, South Korea.

Distributional RL Q-Learning Robotic RL Offline RL Policy Learning

May 2, 2026cs.LG

Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL algorithms achieve favorable sample complexity, but often rely on computationally intractable oracles. In this paper, we use supervised learning as a computational proxy to establish a clear hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs). This hierarchy shows that policy evaluation is the most computationally efficient oracle, provided that supervised learning can be efficiently solved. Motivated by this observation, we propose a novel optimistic actor-critic algorithm that relies solely on the policy evaluation oracle. We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works. We further extend our theoretical results to approximately low-rank MDPs and demonstrate that this setting captures a broad class of real-world environments. Finally, we validate our theoretical results with experiments on several standard Gym environments.

Ruiquan Huang, Donghao Li, Yingbin Liang +1

University of Kentucky. · University of Virginia. · Ohio State University..

Markov Decision Processes Reinforcement Learning Linear Markov Decision Processes Actor-Critic Methods Policy Learning Sample-Efficient RL

Apr 30, 2026cs.LG

Data Deletion Can Help in Adaptive RL

Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) framework, where a family of environments is indexed by a low-dimensional context unknown at test time. The standard approach decomposes the problem: train a so-called "universal policy" which assumes knowledge of the true context, then pair it with a context estimator which approximates context using the observed trajectory. We identify a simple, counterintuitive trick that substantially improves the estimator: randomly delete a fraction of the training buffer after each round. This works because data is collected across multiple rounds using progressively better policies, and older trajectories come from a different distribution than what the estimator will face at deployment time; random deletion creates an implicit exponential decay on older data while preserving diversity without requiring any explicit identification of which samples are stale. This reduces robustness gap by 30% for MLPs and by 6% on average for recurrent networks. Strikingly, it allows a narrow MLP with 5x fewer parameters to outperform a wide MLP trained without deletion. To understand when and why deletion helps, we analyze regularized empirical risk minimization with a mismatch between the train distribution and the distribution at deployment; in this idealized setting, we prove that removing a single uniformly random training point decreases expected test loss in expectation under mild conditions. For ridge regression we make this quantitative: deletion helps when the regularization coefficient is moderate and the signal-to-noise ratio (SNR) is sufficiently low, and, crucially, this SNR threshold gives a direct measure of how large the distribution mismatch between training and deployment must be for deletion to be beneficial.

Param Budhraja, Aditya Gangrade, Alex Olshevsky +1

Department of Electrical and Computer Engineering, Boston University, Boston, MA 02215, USA · Faculty of Electrical and Computer Engineering, Systems Engineering, Boston University, Boston, MA 02215, USA

Non-Stationary RL Reinforcement Learning Distribution Shift Experience Replay Policy Learning

Apr 30, 2026cs.RO

Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?

Policy optimization in high-dimensional continuous control for robotics remains a challenging problem. Predominant methods are inherently local and often require extensive tuning and carefully chosen initial guesses for good performance, whereas more global and less initialization-sensitive search methods typically incur high rollout costs. We propose TFM-S3, a tabular hybrid local-global method for improving global exploration in robot policy learning with limited rollout cost. We interleave high-frequency local updates with intermittent rounds of global search. In each search round, we construct a dynamically updated low-dimensional policy subspace via SVD and perform iterative surrogate-guided refinement within this space. A pretrained tabular foundation model predicts candidate returns from a small context set, enabling large-scale screening with limited rollout cost. Experiments on continuous control benchmarks show that TFM-S3 consistently accelerates early-stage convergence and improves final performance compared to TD3 and population-based baselines under an identical rollout budget. These results demonstrate that foundation models are a powerful new tool for creating sample-efficient policy learning methods for continuous control in robotics.

Buqing Ou, Frederike Dümbgen

Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Inria, Département d’informatique de l’ENS, CNRS, PSL Research University, Paris, France

Tabular Foundation Models Robot Policy Learning Robotic RL RL Exploration Data-Efficient Robot Learning Policy Learning

Apr 30, 2026cs.LG

Bayesian policy gradient and actor-critic algorithms

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which tend to have high variance, requiring many samples and resulting in slow convergence. We first propose a Bayesian framework for policy gradient, based on modeling the policy gradient as a Gaussian process. This reduces the number of samples needed to obtain accurate gradient estimates. Moreover, estimates of the natural gradient and a measure of the uncertainty in the gradient estimates, namely, the gradient covariance, are provided at little extra cost. Since the proposed framework considers system trajectories as its basic observable unit, it does not require the dynamics within trajectories to be of any particular form, and can be extended to partially observable problems. On the downside, it cannot exploit the Markov property when the system is Markovian. To address this, we supplement our Bayesian policy gradient framework with a new actor-critic learning model in which a Bayesian class of non-parametric critics, based on Gaussian process temporal difference learning, is used. Such critics model the action-value function as a Gaussian process, allowing Bayes rule to be used to compute the posterior distribution over action-value functions, conditioned on the observed data. Appropriate choices of the policy parameterization and of the prior covariance (kernel) between action-values yield closed-form expressions for the posterior of the gradient of the expected return with respect to the policy parameters. We perform detailed experimental comparisons of the proposed Bayesian policy gradient and actor-critic algorithms with classic Monte-Carlo based policy gradient methods, on a number of reinforcement learning problems.

Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko

Adobe Research & Inria · Rafael Advanced Defence System, Israel · Inria Lille — SequeL team, France

Bayesian RL Temporal-Difference Learning Policy Gradient Methods Actor-Critic Methods Policy Learning

Apr 28, 2026cs.LG

When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy rewards, such as ranking accuracy, treat incorrect rewards as strictly harmful. In this work, however, we highlight that not all deviations from the ground truth are equal. By theoretically analyzing which outputs attract probability during policy gradient optimization, we categorize reward errors according to their effect on the increase in ground truth reward. The analysis establishes that reward errors, though conventionally viewed as harmful, can also be benign or even beneficial by preventing the policy from stalling around outputs with mediocre ground truth reward. We then present two practical implications of our theory. First, for reinforcement learning from human feedback (RLHF), we develop reward model evaluation metrics that account for the harmfulness of reward errors. Compared to standard ranking accuracy, these metrics typically correlate better with the performance of a language model after RLHF, yet gaps remain in robustly evaluating reward models. Second, we provide insights for reward design in settings with verifiable rewards. A key theme underlying our results is that the effectiveness of a proxy reward function depends heavily on its interaction with the initial policy and learning algorithm.

Shuning Shang, Hubert Strauss, Stanley Wei +2

Princeton Language and Intelligence, Princeton University

Reward Modeling Policy Gradient Policy Learning Reward Design for RL Reward Model Evaluation RL from Human Feedback

Apr 28, 2026cs.AI

Sample-efficient Neuro-symbolic Proximal Policy Optimization

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal Policy Optimization (PPO) that transfers partial logical policy specifications learned in easier instances to guide learning in more challenging settings. We introduce two integrations of symbolic guidance: (i) H-PPO-Product, which biases the action distribution at sampling time, and (ii) H-PPO-SymLoss, which augments the PPO loss with a symbolic regularization term. We evaluate our methods on three benchmarks (OfficeWorld, WaterWorld, and DoorKey), showing consistently faster learning and higher return at convergence than PPO and a Reward Machine baseline, also under imperfect symbolic knowledge.

Simone Murari, Celeste Veronese, Daniele Meli

Dept. of Computer Science, University of Verona, Italy

Reinforcement Learning Proximal Policy Optimization Sparse-Reward RL Policy Learning Sample-Efficient RL

Apr 28, 2026cs.LG

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty

Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly suited for high-dimensional systems with unknown dynamics. We propose Dyna-style Safety Augmented Reinforcement Learning (Dyna-SAuR), a novel algorithm that learns both a scalable safety filter and a control policy using a learned uncertainty-aware dynamics model, while requiring minimal domain knowledge. The filter avoids failures and high uncertainty regions. Thus, better models expand the set of safe and certain states, reducing filter conservatism. We present the effectiveness of Dyna-SAuR on goal-reaching CartPole as well as MuJoCo Walker, reducing failures compared to state-of-the-art methods by 2 orders of magnitude.

Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow +1

Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany

Robot Safety Safety Filtering Safe RL Policy Learning Model-Based RL

Apr 27, 2026cs.DC

Spark Policy Toolkit: Semantic Contracts and Scalable Execution for Policy Learning in Spark

Custom policy-learning pipelines in Spark fail for two coupled systems reasons: rowwise Python execution makes inference impractical, and driver-side candidate materialization makes split search fragile at feature scale. We present Spark Policy Toolkit, a semantics-governed systems toolkit for scalable policy learning in Spark. The toolkit provides two Spark-native primitives: partition-initialized vectorized inference through mapInPandas and mapInArrow, and collect-less split search that scores candidates on executors. Both primitives are governed by one fixed-input semantic contract: the same rows, feature order, treatment vocabulary, preprocessing manifest, and split boundaries must preserve per-row score vectors, best-split decisions, and end-to-end learned policy outputs. The evaluation combines practical baseline ladders, backend parity checks, measured split-search scale results, synthetic and Hillstrom end-to-end policy preservation, missingness stress, partition and order perturbation tests, quantile-boundary sensitivity, and a concrete adversarial failure catalog. On a 40-worker Databricks cluster, mapInArrow reaches 4.72M rows/s at 10M matched rows and 7.23M rows/s at 50M rows, while collect-less split search remains valid from F = 10 through F = 1000 with 124000 candidate rows, where the driver-collect baseline is intentionally skipped. Across 24 backend-ablation settings, mapInArrow wins 18 while mapInPandas wins 6, so the paper treats backend choice as workload-dependent rather than universal. Once the fixed-input lock is enforced, all six tested repartition/coalesce/shuffle perturbations preserve identical signatures; before lock, all six drift. The central result is not speed alone: throughput and collect-less execution are the mechanisms that let policy semantics survive at Spark scale.

Zeyu Bai

Efficient Inference Policy Learning Distributed Inference

Apr 27, 2026cs.AI

Hierarchical Behaviour Spaces

Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option reward functions. We show that, instead of using a single reward function per option, the reward functions can be effectively used to induce a space of behaviours, by letting the controller specify linear combinations over reward functions, allowing a more expressive set of policies to be represented. We call this method Hierarchical Behaviour Spaces (HBS). We evaluate HBS on the NetHack Learning Environment, demonstrating strong performance. We conduct a series of experiments and determine that, perhaps going against conventional wisdom, the benefits of hierarchy in our method come from increased exploration rather than long term reasoning.

Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster +3

Meta Superintelligence Labs · University of Oxford

Reinforcement Learning Hierarchical RL RL Exploration Policy Learning

Apr 25, 2026cs.RO

Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training

Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limited to behaviors observed during post-training? We identify this phenomenon as lock-in: after low-data, supervised fine-tuning (SFT), the policy becomes overly specialized to the post-training data and fails to generalize to novel instructions, manifesting as concept lock-in (fixation on training objects/attributes) and spatial lock-in (fixation on training spatial targets). Many existing remedies introduce additional supervision signals, such as those derived from foundation models or auxiliary objectives, or rely on augmented datasets to recover generalization. In this paper, we show that the policy's internal pre-trained knowledge is sufficient: DeLock mitigates lock-in by preserving visual grounding during post-training and applying test-time contrastive prompt guidance to steer the policy's denoising dynamics according to novel instructions. Across eight simulation and real-world evaluations, DeLock consistently outperforms strong baselines and matches or exceeds the performance of a state-of-the-art generalist policy post-trained with substantially more curated demonstrations.

Suning Huang, Jiaqi Shao, Ke Wang +5

Stanford University

Vision-Language Grounding Vision-Language-Action Models Policy Learning Instruction Generalization in VLA Models

Apr 24, 2026cs.LG

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning

We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for online reward estimation. Instead of relying on fixed heuristics, our method recursively estimates the latent reward mean, smoothing high-variance returns and adapting to non-stationary environments. This approach incurs minimal overhead and requires no modification to existing policy architectures. Experiments on \textit{LunarLander} and \textit{CartPole} demonstrate that Kalman-filtered rewards significantly accelerate convergence and reduce training variance compared to standard normalization techniques. Code is available at https://github.com/Sumxiaa/Kalman_Normalization.

Zixuan Xia, Quanxi Li

University of Bern, Bern, Switzerland.

Reinforcement Learning Policy Gradient Methods Policy Learning

Apr 24, 2026cs.RO

GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories

Imitation learning is a well-established approach for machine-learning-based control. However, its applicability depends on having access to demonstrations, which are often expensive to collect and/or suboptimal for solving the task. In this work, we present GCImOpt, an approach to learn efficient goal-conditioned policies by training on datasets generated by trajectory optimization. Our approach for dataset generation is computationally efficient, can generate thousands of optimal trajectories in minutes on a laptop computer, and produces high-quality demonstrations. Further, by means of a data augmentation scheme that treats intermediate states as goals, we are able to increase the training dataset size by an order of magnitude. Using our generated datasets, we train goal-conditioned neural network policies that can control the system towards arbitrary goals. To demonstrate the generality of our approach, we generate datasets and then train policies for various control tasks, namely cart-pole stabilization, planar and three-dimensional quadcopter stabilization, and point reaching using a 6-DoF robot arm. We show that our trained policies can achieve high success rates and near-optimal control profiles, all while being small (less than 80,000 neural network parameters) and fast enough (up to more than 6,000 times faster than a trajectory optimization solver) that they could be deployed onboard resource-constrained controllers. We provide videos, code, datasets and pre-trained policies under a free software license; see our project website https://jongoiko.github.io/gcimopt/.

Jon Goikoetxea, Jesús F. Palacián

Department of Statistics, Mathematics and Computer Science, Public University of Navarre · Ensimag, Institut National Polytechnique de Grenoble, Universit´e Grenoble Alpes · Institute for Advanced Materials and Mathematics (InaMat2)

Robotic Control Imitation Learning Policy Learning

Apr 24, 2026cs.LG

Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning

One-step offline RL actors are attractive because they avoid backpropagating through long iterative samplers and keep inference cheap, but they still have to improve under a critic without drifting away from actions that the dataset can support. In recent one-step extraction pipelines, a strong iterative teacher provides one target action for each latent draw, and the same student output is asked to do both jobs: move toward higher Q and stay near that paired endpoint. If those two directions disagree, the loss resolves them as a compromise on that same sample, even when a nearby better action remains locally supported by the data. We propose DROL, a latent-conditioned one-step actor trained with top-1 dynamic routing. For each state, the actor samples

K

candidate actions from a bounded latent prior, assigns each dataset action to its nearest candidate, and updates only that winner with Behavior Cloning and critic guidance. Because the routing is recomputed from the current candidate geometry, ownership of a supported region can shift across candidates over the course of learning. This gives a one-step actor room to make local improvements that pointwise extraction struggles to capture, while retaining single-pass inference at test time. On OGBench and D4RL, DROL is competitive with the one-step FQL baseline, improving many OGBench task groups while remaining strong on both AntMaze and Adroit. Project page: https://muzhancun.github.io/preprints/DROL.

Zhancun Mu, Guangyu Zhao, Yiwu Zhong +1

School of Intelligence Science and Technology, Peking University

Reinforcement Learning Offline RL Policy Learning

Apr 23, 2026cs.LG

Insect-inspired modular architectures as inductive biases for reinforcement learning

Most reinforcement-learning (RL) controllers used in continuous control are architecturally centralized: observations are compressed into a single latent state from which both value estimates and actions are produced. Biological control systems are often organized differently. Insects, in particular, coordinate navigation, heading stabilization, memory, and context-dependent action selection through distributed circuits rather than a single monolithic controller. Motivated by this contrast, we study an RL policy architecture that decomposes control into interacting modules for sensory encoding, heading representation, sparse associative memory, recurrent command generation, and local motor control, with a learned arbitration mechanism that allocates motor authority across modules. The model is evaluated on a two-dimensional navigation task that require simultaneous food seeking, obstacle avoidance, and predator escape. In a six-seed predator-navigation experiment trained with Proximal Policy Optimization (PPO) for 75 updates, the modular policy achieves the strongest final mean performance among the tested controllers, with final episodic return

-2798.8\pm964.4

versus

-3778.0\pm628.1

for a centralized gated recurrent unit (GRU) and

-4727.5\pm772.5

for a centralized multilayer perceptron (MLP). The modular policy also attains the lowest final value loss and stable PPO optimization statistics while driving module-assignment entropy to

0.0457\pm0.0244

, indicating highly selective control allocation. These results suggest that distributed control can serve as a useful inductive bias for RL problems involving dynamically competing behavioral objectives.

Anne E. Staples

Department of Mechanical Engineering, Virginia Tech, Blacksburg, Virginia 24061, USA

RL Control Reinforcement Learning Policy Learning