Reinforcement Learning

Also known as RL

Ask about this topic

Overview

Reinforcement learning studies how an agent can choose actions over time to earn rewards, using experience to improve its decisions. Common approaches include value-based methods such as Q-learning, policy-gradient methods such as PPO, and model-based methods that learn or use a model of the environment; offline and hierarchical methods address learning from fixed data and long tasks. Applications range from Atari and MuJoCo benchmarks to robot control, traffic, games, and language-model agents that use tools or solve multi-step problems. A central challenge is making learning efficient and reliable when rewards are sparse or imperfect, environments change, and success in simulation or benchmarks may not transfer safely to deployment.

Latest papers

CardsList

1,743 papers237 papers in the last four weeks, up 46% on the four weeks before. 1.4% of all new papers.

Mar 12, 2026

Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics

Cross-domain reinforcement learning (CDRL) is meant to improve the data efficiency of RL by leveraging the data samples collected from a source domain to facilitate the learning in a similar target domain. Despite its potential, cross-domain transfer in RL is known to have two fundamental and intertwined challenges: (i) The source and target domains can have distinct state space or action space, and this makes direct transfer infeasible and thereby requires more sophisticated inter-domain mappings; (ii) The transferability of a source-domain model in RL is not easily identifiable a priori, and hence CDRL can be prone to negative effect during transfer. In this paper, we propose to jointly tackle these two challenges through the lens of cross-domain Bellman consistency and hybrid critic. Specifically, we first introduce the notion of cross-domain Bellman consistency as a way to measure transferability of a source-domain model. Then, we propose QQAvatar, which combines the Q functions from both the source and target domains with an adaptive hyperparameter-free weight function. Through this design, we characterize the convergence behavior of QQAvatar and show that QQAvatar achieves reliable transfer in the sense that it effectively leverages a source-domain Q function for knowledge transfer to the target domain. Through experiments, we demonstrate that QQAvatar achieves favorable transferability across various RL benchmark tasks, including locomotion and robot arm manipulation. Our code is available at https://rl-bandits-lab.github.io/Cross-Domain-RL/.

Ming-Hong Chen, Kuan-Chen Pan, You-De Huang +2

National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Applied Machine Learning, Meta AI, Menlo Park, CA, USA

Reinforcement LearningCross-Domain Transfer LearningTask Transferability Estimation
AskPDF
Mar 12, 2026

From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis that yields three key insights: (1) CoT expands the generative exploration space, while RL contracts it toward high-reward regions; (2) final reward is strongly negatively correlated with both the mean and variance of image-token entropy, highlighting the need to reduce uncertainty and instability; and (3) the entropy of the textual CoT directly governs downstream image quality, with lower-entropy CoTs leading to better generations. Motivated by these findings, we propose Entropy-Guided Group Relative Policy Optimization (EG-GRPO), a fine-tuning strategy that reallocates optimization budget by uncertainty: low-entropy tokens are excluded from reward-driven updates to preserve stability, while high-entropy tokens receive an entropy bonus that encourages structured exploration without collapse. Experiments on standard T2I benchmarks demonstrate that EG-GRPO achieves state-of-the-art performance.

Han Song, Yucheng Zhou, Jianbing Shen +1

The Chinese University of Hong Kong · University of Macau

Image GenerationAutoregressive Image GenerationRL for Image GenerationReinforcement LearningGroup Relative Policy Optimization
AskPDF
Mar 12, 2026

Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization

Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms -- assumed known a priori -- directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization objective to enforce energy-efficient control. A complete theoretical foundation is established: functional independence of shaping and regularization, energy-based gradient enrichment under positive-definite Hessian conditions, convergence guarantees under function approximation, and approximate potential error bounds. Across four continuous control benchmarks and four baseline algorithms, H-EARS achieves consistent gains in convergence speed, policy stability, and final performance. High-fidelity vehicle simulations validate applicability in safety-critical settings under extreme road conditions.

Qijun Liao, Jue Yang, Yiting Kang +3

School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, China · Jiangsu XCMG Construction Machinery Research Institute Co., Ltd., Jiangsu 221000, China

RL ControlReinforcement LearningReward ShapingReward Design for RLPhysics-Informed RL
AskPDF
Mar 11, 2026

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a policy that conditions on past episodes and adapts its search strategy across episodes. MR-Search learns to learn a search strategy with self-reflection, allowing search agents to improve in-context exploration at test-time. Specifically, MR-Search performs cross-episode exploration by generating explicit self-reflections after each episode and leveraging them as additional context to guide subsequent attempts, thereby promoting more effective exploration during test-time. We further introduce a multi-turn RL algorithm that estimates a dense relative advantage at the turn level, enabling fine-grained credit assignment on each episode. Empirical results across various benchmarks demonstrate the advantages of MR-Search over baselines based RL, showing strong generalization and relative improvements of 9.2% to 19.3% across eight benchmarks. Our code and data are available at https://github.com/tengxiao1/MR-Search.

Teng Xiao, Yige Yuan, Hamish Ivison +6

Allen Institute for AI · University of Washington · Independent

Reinforcement LearningAgentic SearchMeta-Reinforcement LearningAgentic RLRL ExplorationIn-Context RL
AskPDF
Mar 11, 2026

Hindsight-Anchored Policy Optimization: Learning Through Hindsight with Thompson Sampling-Inspired Adaptive Gating

Reinforcement Learning with Verifiable Rewards improves reasoning in large language models, yet on-policy learning often suffers from cold-start challenges in sparse-reward settings. Recent mixed-policy approaches address this by combining off-policy teacher data with on-policy training. However, simply combining these introduce a persistent off-policy gradient mass that risks training collapse and instability. To address this challenge, we propose Hindsight-Anchored Policy Optimization (HAPO), a framework that allows teacher intervention to act as a temporary support. HAPO employs Beta-Binomial confidence gating, an adaptive gating mechanism that decides when to open the gate for teacher intervention. The intervention operates with Synthetic Success Injection, which replaces the group's lowest-reward rollout with a verified teacher trajectory. We also introduce adaptive threshold annealing, which gradually retracts the support and restores on-policy training within a finite horizon to mitigate persistent off-policy drift. We demonstrate that HAPO can be layered on top of existing mixed-policy methods in a generalizable manner. Across six math reasoning benchmarks and two model scales, HAPO improves the average accuracy of three major mixed-policy methods while maintaining training stability.

Yuning Wu, Ke Wang, Haoran Liu +3

Amazon

Reinforcement LearningRL for Language Model ReasoningReinforcement Learning with Verifiable RewardsSparse-Reward RLOff-Policy RL
AskPDF
Mar 11, 2026

Ergodicity in reinforcement learning

In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewards is non-ergodic, the expected value, i.e., the average over infinitely many trajectories with a given policy, is uninformative for the average over a single, but infinitely long trajectory. Thus, if we care about how the individual agent performs during deployment, the expected value is not a good optimization objective. In this paper, we discuss the impact of non-ergodic reward processes on reinforcement learning agents through an instructive example, relate the notion of ergodic reward processes to more widely used notions of ergodic Markov chains, and present existing solutions that optimize long-term performance of individual trajectories under non-ergodic reward dynamics.

Dominik Baumann, Erfaun Noorani, Arsenii Mustafin +5

Cyber-physical Systems Group, Aalto University, Espoo 02150, Finland · Control & Autonomous Systems Engineering Group, MIT Lincoln Laboratory, Lexington, MA 02421-6426, USA · Data Analytics Lab, Vrije Universiteit Brussel, Brussel 1050, Belgium +2

Reinforcement LearningAverage-Reward RL
AskPDF
Mar 11, 2026

Learning to Score: Tuning Cluster Schedulers through Reinforcement Learning

Efficiently allocating incoming jobs to nodes in large-scale clusters can lead to substantial improvements in both cluster utilization and job performance. In order to allocate incoming jobs, cluster schedulers usually rely on a set of scoring functions to rank feasible nodes. Results from individual scoring functions are usually weighted equally, which could lead to sub-optimal deployments as the one-size-fits-all solution does not take into account the characteristics of each workload. Tuning the weights of scoring functions, however, requires expert knowledge and is computationally expensive. This paper proposes a reinforcement learning approach for learning the weights in scheduler scoring algorithms with the overall objective of improving the end-to-end performance of jobs for a given cluster. Our approach is based on percentage improvement reward, frame-stacking, and limiting domain information. We propose a percentage improvement reward to address the objective of multi-step parameter tuning. The inclusion of frame-stacking allows for carrying information across an optimization experiment. Limiting domain information prevents overfitting and improves performance in unseen clusters and workloads. The policy is trained on different combinations of workloads and cluster setups. We demonstrate the proposed approach improves performance on average by 33% compared to fixed weights and 12% compared to the best-performing baseline in a lab-based serverless scenario.

Martin Asenov, Qiwen Deng, Gingfung Yeung +1

Edinburgh Research Centre, Central Software Institute, Huawei · School of Computer Science, University of St Andrews

Learning to OptimizeReinforcement LearningReward Design for RL
AskPDF
Mar 10, 2026

GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning

A commonly used family of RL algorithms for diffusion policies conducts softmax reweighting over samples from the behavior policy, which often induces an overgreedy policy and fails to utilize feedback from negative samples. In this work, we introduce GeMPO, a simple and unified framework that generalizes reweighting scheme in diffusion RL from softmax to general monotonic functions. GeMPO revisits diffusion RL via a measure matching perspective: First, we construct a virtual target policy measure via solving a regularized policy optimization objective; Second, we minimize the divergence between the current policy and this target measure through reweighted flow matching. This formulation offers two key advantages: i) It extends weight design beyond traditional exponential reweighting, allowing it to be tailored to diverse reward landscapes; and ii) by relaxing the non-negativity constraint on the target measure, our framework provides a principled justification for negative reweighting. We provide interpretations of how negative reweighting actively repels the policy from suboptimal actions and thus facilitates exploration. Extensive empirical evaluations demonstrate that GeMPO achieves competitive or superior performance by leveraging these flexible weighting schemes, and we provide practical guidelines for selecting reweighting methods in practice.

Haitong Ma, Chenxiao Gao, Tianyi Chen +2

Harvard University · Georgia Institute of Technology

Reinforcement LearningRL for Diffusion ModelsDiffusion Policy
AskPDF
Mar 10, 2026

Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces

Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than standard PMD, enabling the use of approximate advantage (or Q-) functions while retaining strong convergence guarantees. However, applying PDA in continuous state and action spaces remains computationally challenging, since action selection involves solving an optimization sub-problem at each decision step. In this paper, we propose actor-accelerated PDA, which uses a learned policy network to approximate the solution of the optimization sub-problems, yielding faster runtimes while maintaining convergence guarantees. We provide a theoretical analysis that quantifies how actor approximation error impacts the convergence of PDA under suitable assumptions. We then evaluate its performance on several benchmarks in robotics, control, and operations research problems. Actor-accelerated PDA achieves superior performance compared to popular on-policy baselines such as Proximal Policy Optimization (PPO). Overall, our results bridge the gap between the theoretical advantages of PDA and its practical deployment in continuous-action problems with function approximation.

Ji Gao, Caleb Ju, Guanghui Lan +1

School of Chemical and Biomolecular Engineering, Georgia Institute of Technology, GA, USA. · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, GA, USA. · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, GA, USA

Reinforcement LearningPolicy OptimizationPolicy Learning
AskPDF
Mar 10, 2026

OpenClaw-RL: Train Any Agent Simply by Talking

Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present OpenClaw-RL, a framework that employs next-state signals to optimize personal agents online through infrastructure and methodology innovations. On the infrastructure side, we extend existing RL systems to a server-client architecture where the RL server hosts the policy behind an inference API and user terminals stream interaction data back over HTTP. From each observed next state, the system extracts two complementary training signals, evaluative and directive, via a separate asynchronous server so that neither signal extraction nor optimization blocks inference. On the methodology side, we introduce a hybrid RL objective that unifies both signal types in a single update: directive signals provide richer, token-level supervision but are sparser, while evaluative signals are more broadly available. To stabilize distillation under teacher-student mismatch, we propose overlap-guided hint selection, which picks the hint whose induced teacher distribution maximally overlaps with the student's top-kk tokens, together with a log-probability-difference clip that bounds per-token advantages. Applied to personal agents, OpenClaw-RL enables an agent to improve simply by being used, recovering conversational signals from user re-queries, corrections, and explicit feedback. Applied to general agents, OpenClaw-RL is the first RL framework to unify real-world agent settings spanning terminal, GUI, SWE, and tool-call environments, where we additionally demonstrate the utility of next-state signals in long-horizon settings.

Yinjie Wang, Xuyang Chen, Xiaolong Jin +2

Agentic RLReinforcement LearningRL for Tool Use
AskPDF
Mar 10, 2026

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

Deep Reinforcement Learning systems are highly sensitive to the learning rate (LR), and selecting stable and performant training runs often requires extensive hyperparameter search. In Proximal Policy Optimization (PPO) actor--critic methods, small LR values lead to slow convergence, whereas large LR values may induce instability or collapse. We analyse this phenomenon from the behavior of the hidden neurons in the network using the Overfitting-Underfitting Indicator (OUI), a metric that quantifies the balance of binary activation patterns over a fixed probe batch. We introduce an efficient batch-based formulation of OUI and derive a theoretical connection between LR and activation sign changes, clarifying how a correct evolution of the neuron's inner structure depends on the step size. Empirically, across three discrete-control environments and multiple seeds, we show that OUI measured at only 10% of training already discriminates between LR regimes. We observe a consistent asymmetry: critic networks achieving highest return operate in an intermediate OUI band (avoiding saturation), whereas actor networks achieving highest return exhibit comparatively high OUI values. We then compare OUI-based screening rules against early return, clip-based, divergence-based, and flip-based criteria under matched recall over successful runs. In this setting, OUI provides the strongest early screening signal: OUI alone achieves the best precision at broader recall, while combining early return with OUI yields the highest precision in best-performing screening regimes, enabling aggressive pruning of unpromising runs without requiring full training.

Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre +3

Universitat Polit`ecnica de Val`encia, Valencia, Spain · Universitat Jaume I, Castell´o de la Plana, Spain · Openchip & Software Technologies, Barcelona, Spain

Reinforcement LearningProximal Policy OptimizationNeural Network Training DynamicsActor-Critic Methods
AskPDF
Mar 10, 2026

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space

Offline-to-online reinforcement learning (RL) offers a promising paradigm for robotics by pre-training policies on safe, offline demonstrations and fine-tuning them via online interaction. However, a fundamental challenge remains: how to safely explore online without deviating from the behavioral support of the offline data? While recent methods leverage conditional variational autoencoders (CVAEs) to bound exploration within a latent space, they inherently suffer from an exploitation gap -- a performance ceiling imposed by the decoder's reconstruction loss. We introduce SPAARS, a curriculum learning framework that initially constrains exploration to the low-dimensional latent manifold for sample-efficient, safe behavioral improvement, then seamlessly transfers control to the raw action space, bypassing the decoder bottleneck. SPAARS has two instantiations: the CVAE-based variant requires only unordered (s,a) pairs and no trajectory segmentation; SPAARS-SUPE pairs SPAARS with OPAL temporal skill pretraining for stronger exploration structure at the cost of requiring trajectory chunks. We prove an upper bound on the exploitation gap using the Performance Difference Lemma, establish that latent-space policy gradients achieve provable variance reduction over raw-space exploration, and show that concurrent behavioral cloning during the latent phase directly controls curriculum transition stability. Empirically, SPAARS-SUPE achieves 0.825 normalized return on kitchen-mixed-v0 versus 0.75 for SUPE, with 5x better sample efficiency; standalone SPAARS achieves 92.7 and 102.9 normalized return on hopper-medium-v2 and walker2d-medium-v2 respectively, surpassing IQL baselines of 66.3 and 78.3 respectively, confirming the utility of the unordered-pair CVAE instantiation.

Swaminathan S K, Aritra Hazra

Department of Computer Science and Engineering, IIT Kharagpur

Reinforcement LearningOffline-To-Online RLRL ExplorationSafe RLSample-Efficient RLCurriculum RL
AskPDF
Mar 10, 2026

MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics

Multi-objective reinforcement learning (MORL) is a powerful tool to learn Pareto-optimal policy families across conflicting objectives. However, unlike traditional RL algorithms, existing MORL algorithms do not effectively leverage large-scale parallelization to concurrently simulate thousands of environments, thus facing vastly increased computation time. Ultimately, this has limited the application of MORL towards complex multi-objective robotics problems. To address these challenges, we present 1) MORLAX, a new GPU-native, fast MORL algorithm, and 2) MO-Playground, a pip-installable playground of GPU-accelerated multi-objective environments. Together, MORLAX and MO-Playground approximate Pareto sets within minutes, offering 26-271x speed-ups compared to legacy CPU-based approaches and up to 19x speed-ups over prior GPU-based approaches whilst learning superior Pareto front hypervolumes. We demonstrate MO-Playground's versatility by implementing a custom BRUCE humanoid robot environment and learning Pareto-optimal locomotion policies across 6 practical objectives in simulation, such as smoothness, efficiency and arm swinging. Our toolbox is available at https://dynamicmobility.github.io/moplayground/.

Neil Janwani, Ellen Novoseller, Vernon J. Lawhern +1

Georgia Institute of Technology, Atlanta, GA USA · DEVCOM Army Research Laboratory, MD, USA

GPU-Accelerated RLMulti-Objective Reinforcement LearningReinforcement LearningRL for Robotics
AskPDF
Mar 10, 2026

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models become excessively over-confident in incorrect answers. Previous studies devote to directly incorporating calibration objective into existing optimization target. However, our theoretical analysis demonstrates that there exists a fundamental gradient conflict between the optimization for maximizing policy accuracy and minimizing calibration error. Building on this insight, we propose DCPO, a simple yet effective framework that systematically decouples reasoning and calibration objectives. Extensive experiments demonstrate that our DCPO not only preserves accuracy on par with GRPO but also achieves the best calibration performance and substantially mitigates the over-confidence issue. Our study provides valuable insights and practical solution for more reliable LLM deployment.

Zhengzhao Ma, Xueru Wen, Boxi Cao +6

Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +2

Reinforcement LearningRL for Language Model ReasoningLanguage Model CalibrationReinforcement Learning with Verifiable Rewards
AskPDF
Mar 9, 2026

A Survey of Reinforcement Learning For Economics

This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably "small" problems or our ability to convert "big" problems into smaller ones. While this reduction has been sufficient for many classical applications, a growing class of economic models resists such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming, extending tractability to problems with high-dimensional states, continuous actions, and strategic interactions. I review the theory connecting classical planning to modern learning algorithms and demonstrate their mechanics through simulated examples in pricing, inventory control, strategic games, and preference elicitation. I also examine the practical vulnerabilities of these algorithms, noting their brittleness, sample inefficiency, sensitivity to hyperparameters, and the absence of global convergence guarantees outside of tabular settings. The successes of reinforcement learning remain strictly bounded by these constraints, as well as a reliance on accurate simulators. When guided by economic structure, reinforcement learning provides a remarkably flexible framework. It stands as an imperfect, but promising, addition to the computational economist's toolkit. A companion survey (Rust and Rawat, 2026b) covers the inverse problem of inferring preferences from observed behavior. All simulation code is publicly available.

Pranjal Rawat

Georgetown University

Reinforcement Learning
AskPDF
Mar 9, 2026

Multi-level meta-reinforcement learning with skill-based curriculum

We consider problems in sequential decision making with natural multi-level structure, where sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure has remained a longstanding challenge; we describe an efficient multi-level procedure for repeatedly compressing Markov decision processes (MDPs), wherein a parametric family of policies at one level is treated as single actions in the compressed MDPs at higher levels, while preserving the semantic meanings and structure of the original MDP, and mimicking the natural logic to address a complex MDP. Higher-level MDPs are themselves independent MDPs with less stochasticity, and may be solved using existing algorithms. As a byproduct, spatial or temporal scales may be coarsened at higher levels, making it more efficient to find long-term optimal policies. The multi-level representation delivered by this procedure decouples sub-tasks from each other and usually greatly reduces unnecessary stochasticity and the policy search space, leading to fewer iterations and computations when solving the MDPs. A second fundamental aspect of this work is that these multi-level decompositions plus the factorization of policies into embeddings (problem-specific) and skills (including higher-order functions) yield new transfer opportunities of skills across different problems and different levels. This whole process is framed within curriculum learning, wherein a teacher organizes the student agent's learning process in a way that gradually increases the difficulty of tasks and and promotes transfer across MDPs and levels within and across curricula. The consistency of this framework and its benefits can be guaranteed under mild assumptions. We demonstrate abstraction, transferability, and curriculum learning in examples, including MazeBase+, a more complex variant of the MazeBase example.

Sichen Yang, Mauro Maggioni

Johns Hopkins University · Department of Applied Mathematics & Statistics Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA · Department of Mathematics, Department of Applied Mathematics & Statistics Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA

Reinforcement LearningHierarchical RLMeta-Reinforcement LearningState AbstractionCurriculum RLMulti-Task RL
AskPDF
Mar 9, 2026

Embedding Classical Balance Control Principles in Reinforcement Learning for Humanoid Recovery

Humanoid robots remain vulnerable to falls and unrecoverable failure states, limiting their practical utility in unstructured environments. While reinforcement learning has demonstrated stand-up behaviors, existing approaches treat recovery as a pure task-reward problem without an explicit representation of the balance state. We present a unified RL policy that addresses this limitation by embedding classical balance metrics: capture point, center-of-mass state, and centroidal momentum, as privileged critic inputs and shaping rewards directly around these quantities during training, while the actor relies solely on proprioception for zero-shot hardware transfer. Without reference trajectories or scripted contacts, a single policy spans the full recovery spectrum: ankle and hip strategies for small disturbances, corrective stepping under large pushes, and compliant falling with multi-contact stand-up using the hands, elbows, and knees. Trained on the Unitree H1-2 in Isaac Lab, the policy achieves a 93.4% recovery rate across randomized initial poses and unscripted fall configurations. An ablation study shows that removing the balance-informed structure causes stand-up learning to fail entirely, confirming that these metrics provide a meaningful learning signal rather than incidental structure. Sim-to-sim transfer to MuJoCo and preliminary hardware experiments further demonstrate cross-environment generalization. These results show that embedding interpretable balance structure into the learning framework substantially reduces time spent in failure states and broadens the envelope of autonomous recovery.

Nehar Poddar, Stephen McCrory, Luigi Penco +3

Florida Institute for Human and Machine Cognition, Pensacola, FL, USA. · University of West Florida, Pensacola, FL, USA.

Humanoid Robot Fall RecoveryHumanoid Robot ControlHumanoid RoboticsReinforcement Learning
AskPDF
Mar 9, 2026

Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control

State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computational complexity is often incompatible with the constraints of resource-limited hardware, due to their reliance on replay buffers, batch updates, and target networks. The emerging paradigm of streaming deep RL addresses this limitation through purely online updates, achieving strong empirical performance on standard benchmarks. In this work, we propose two novel streaming deep RL algorithms, Streaming Soft Actor-Critic (S2AC) and Streaming Deterministic Actor-Critic (SDAC), explicitly designed to be compatible with state-of-the-art batch RL methods, making them particularly suitable for on-device finetuning applications such as Sim2Real transfer. Both algorithms achieve performance comparable to state-of-the-art streaming baselines on standard benchmarks without requiring tedious per-environment hyperparameter tuning. We further investigate the batch-to-streaming transition, showing that a naive transition does not guarantee preservation of pre-trained policy performance, and propose a principled approach to address this challenge.

Riccardo De Monte, Matteo Cederle, Gian Antonio Susto

Department of Information Engineering, University of Padova

Reinforcement LearningContinuous ControlOff-Policy RLOffline-To-Online RL
AskPDF
Mar 9, 2026

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Standard reinforcement learning (RL) for large language model (LLM) agents primarily optimizes extrinsic task rewards, often favoring isolated task completion over continual adaptation. This paradigm can cause premature convergence to suboptimal policies and leaves useful experience only implicitly encoded in model parameters, limiting its retrieval and reuse for future decisions. We introduce RetroAgent, an online RL framework that trains agents to master interactive environments not merely by solving tasks, but by evolving across episodes. Inspired by human retrospective self-improvement, RetroAgent augments extrinsic rewards with hindsight-generated dual intrinsic feedback: (1) Intrinsic Numerical Feedback, which rewards beneficial exploration by measuring incremental subtask progress relative to prior attempts; and (2) Intrinsic Language Feedback which distills successes and failures into reusable textual lessons for explicit experience reuse. To leverage these lessons effectively, we propose Similarity & Utility-Aware Upper Confidence Bound (SimUtil-UCB), a retrieval strategy that balances semantic relevance, historical utility, and exploration. Across four challenging agentic benchmarks, RetroAgent achieves new state-of-the-art performance, outperforming GRPO by +18.3% on ALFWorld, +15.4% on WebShop, +27.1% on Sokoban, and +8.9% on MineSweeper, while demonstrating strong test-time adaptation and out-of-distribution generalization.

Xiaoying Zhang, Zichen Liu, Yipeng Zhang +2

Shanghai AI Lab · National University of Singapore · Independent Researcher

Reinforcement LearningRL for LLM AgentsContinual Learning for LLM AgentsMemory-Augmented Language Model Agents
AskPDF
Mar 9, 2026

Impact of Connectivity on Laplacian Representations in Reinforcement Learning

Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories. In this work, we prove an upper bound on the approximation error of linear value function approximation under the learned spectral features. We show how this error scales with the algebraic connectivity of the state-graph, grounding the approximation quality in the topological structure of the MDP. We further bound the error introduced by the eigenvector estimation itself, leading to an end-to-end error decomposition across the representation learning pipeline. Additionally, our expression of the Laplacian operator for the RL setting, although equivalent to existing ones, prevents some common misunderstandings, of which we show some examples from the literature. Our results hold for general (non-uniform) policies without any assumptions on the symmetry of the induced transition kernel. We validate our theoretical findings with numerical simulations on gridworld environments.

Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang +2

Baker Hughes, Florence, Italy · Politecnico di Milano · University College London, AI Center (UCL) +1

Reinforcement LearningRepresentation Learning for RLState Representation LearningFunction Approximation in RLValue Function Estimation
AskPDF
Mar 9, 2026

CRED: Counterfactual Reasoning and Environment Design for Active Preference Learning

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach. These systems benefit strongly by being able to align their behavior to reflect human preferences and respond to corrections, but manually encoding this feedback is infeasible. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods sample from fixed trajectory sets or replay buffers that limit query diversity and often fail to identify informative comparisons. We propose CRED, a novel trajectory generation method for APL that improves reward inference by jointly optimizing environment design and trajectory selection to efficiently query and extract preferences from users. CRED "imagines" new scenarios through environment design and leverages counterfactual reasoning -- by sampling possible rewards from its current belief and asking "What if this were the true preference?" -- to generate trajectory pairs that expose differences between competing reward functions. Comprehensive experiments and a user study show that CRED significantly outperforms state-of-the-art methods in reward accuracy and sample efficiency and receives higher user ratings.

Yi-Shiuan Tung, Gyanig Kumar, Wei Jiang +2

Department of Computer Science, University of Colorado Boulder

Active Preference LearningPreference LearningPreference-Based RLReward ModelingPairwise Preference LearningReinforcement Learning
AskPDF
Mar 9, 2026

Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces

We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm. Posterior sampling is a heuristic for decision-making under uncertainty that has been used to develop successful algorithms for a variety of continuous control problems. However, theoretical work on GP-PSRL is limited. All known regret bounds either have a sub-optimal growth rate, require strong smoothness assumptions, or fail to properly account for the fact that the set of possible system states is unbounded. Through a recursive application of the Borell-Tsirelson-Ibragimov-Sudakov inequality, we show that, with high probability, the states actually visited by the algorithm are contained within a ball of near-constant radius. We then use the chaining method to control the regret suffered by GP-PSRL under weak smoothness conditions. Our main result is a Bayesian regret bound of the order O~(HγTT)\widetilde{\mathcal{O}}(H\sqrt{γ_TT}), where HH is the horizon, TT is the number of time steps and γTγ_T is the expected information gain. With this result, we resolve the limitations with prior theoretical work on PSRL, and provide the theoretical foundation and tools for analyzing PSRL in complex settings.

Hamish Flynn, Joe Watson, Ingmar Posner +1

Carnegie Mellon University · University of Oxford · Technical University of Darmstadt +2

RL ControlRegret Minimization in RLReinforcement LearningBayesian RLGaussian ProcessesPosterior Sampling
AskPDF
Mar 9, 2026

RL unknotter, hard unknots and unknotting number

We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for navigating Reidemeister moves. The pipeline applies to arbitrary knots and links; we test it on ``very hard'' unknot diagrams and, using diagram inflation, on 41#9104_1\#9_{10} where we investigate the recently established and surprising upper bound of three for the unknotting number. In addition, we explain a self-improving workbook-driven extension of the pipeline that systematically improves unknotting number upper bounds on the prime knots.

Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer

Reinforcement Learning
AskPDF
Mar 9, 2026

Robust Transfer Learning with Side Information

Robust Markov Decision Processes (MDPs) address environmental shift through distributionally robust optimization (DRO) by finding an optimal worst-case policy within an uncertainty set of transition kernels. However, standard DRO approaches require enlarging the uncertainty set under large shifts, which leads to overly conservative and pessimistic policies. In this paper, we propose a framework for transfer under environment shift that derives a robust target-domain policy via estimate-centered uncertainty sets, constructed through constrained estimation that integrates limited target samples with side information about the source-target dynamics. The side information includes bounds on feature moments, distributional distances, and density ratios, yielding improved kernel estimates and tighter uncertainty sets. The side information includes bounds on feature moments, distributional distances, and density ratios, yielding improved kernel estimates and tighter uncertainty sets. Error bounds and convergence results are established for both robust and non-robust value functions. Moreover, we provide a finite-sample guarantee on the learned robust policy and analyze the robust sub-optimality gap. Under mild low-dimensional structure on the transition model, the side information reduces this gap and improves sample efficiency. We assess the performance of our approach across OpenAI Gym environments and classic control problems, consistently demonstrating superior target-domain performance over state-of-the-art robust and non-robust baselines.

Akram S. Awad, Shihab Ahmed, Yue Wang +1

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

Reinforcement LearningRobust Markov Decision ProcessesDistributionally Robust RLDistributionally Robust OptimizationSample-Efficient RL
AskPDF
Mar 8, 2026

TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step diffusion models strongly rely on back-propagating through differentiable reward models, thereby excluding the majority of important real-world reward signals, e.g., non-differentiable rewards such as humans' binary likeness, object counts, etc. To properly incorporate non-differentiable rewards to improve few-step generative models, we introduce TDM-R1, a novel reinforcement learning paradigm built upon a leading few-step model, Trajectory Distribution Matching (TDM). TDM-R1 decouples the learning process into surrogate reward learning and generator learning. Furthermore, we developed practical methods to obtain per-step reward signals along the deterministic generation trajectory of TDM, resulting in a unified RL post-training method that significantly improves few-step models' ability with generic rewards. We conduct extensive experiments ranging from text-rendering, visual quality, and preference alignment. All results demonstrate that TDM-R1 is a powerful reinforcement learning paradigm for few-step text-to-image models, achieving state-of-the-art reinforcement learning performances on both in-domain and out-of-domain metrics. Furthermore, TDM-R1 also scales effectively to the recent strong Z-Image model, consistently outperforming both its 100-NFE and few-step variants with only 4 NFEs. Project page: https://github.com/Luo-Yihong/TDM-R1

Yihong Luo, Tianyang Hu, Weijian Luo +1

Hong Kong University of Science and Technology · The Chinese University of Hong Kong, Shenzhen · hi-Lab, Xiaohongshu Inc +1

RL for Diffusion ModelsReinforcement LearningT2I Diffusion ModelsFew-Step Diffusion SamplingReward Modeling
AskPDF
Mar 8, 2026

Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving

Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unbounded and open-ended, demanding exploration across vast and flexible solution spaces. Existing approaches, whether purely learning-based or reliant on carefully designed workflows, often suffer from limited exploration efficiency and poor generalization. To overcome these challenges, we present HELIX -- a Hierarchical Evolutionary reinforcement Learning framework with In-context eXperiences. HELIX introduces two key novelties: (i) a diverse yet high-quality pool of candidate solutions that broadens exploration through in-context learning, and (ii) reinforcement learning for iterative policy refinement that progressively elevates solution quality. This synergy enables the discovery of more advanced solutions. On the circle packing task, HELIX achieves state-of-the-art result with a sum of radii of 2.63598308 using only a 14B model. Across standard machine learning benchmarks, HELIX further surpasses GPT-4o with a carefully engineered pipeline, delivering an average F1 improvement of 5.95 points on the Adult and Bank Marketing datasets.

Chang Su, Zhongkai Hao, Zhizhou Zhang +4

Bosch (China) Investment Co., Ltd. · Tsinghua-Bosch Joint Center for ML, Tsinghua University · Dept. of Comp. Sci. & Techn., Tsinghua University +1

Evolutionary RLReinforcement LearningRL for Language ModelsHierarchical RLLarge Language Model-Guided Scientific Discovery
AskPDF
Mar 7, 2026

Re2\textbf{Re}^{2}: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still tend to generate unnecessary and low-quality steps in their chain-of-thought (CoT), leading to inefficient overthinking and lower answer quality. We show that when the initial direction or quality of the CoT is suboptimal, the model often fails to reach the correct answer, even after generating several times more tokens than when the initial CoT is well-initialized. To this end, we introduce Reinforcement Learning with Re-solving (Re2^2), in which LLMs learn to flexibly abandon unproductive reasoning paths and restart the solution process when necessary, rather than always committing to a final answer. Re2^2 applies pure reinforcement learning without any preliminary supervised fine-tuning, successfully amplifying the rare redo behavior in vanilla models from only 0.5% to over 30%. This leads to substantial performance gains over standard RLVR under the same training compute budget, and also demonstrates notable improvements in test-time performance as the number of samples increases.

Pinzheng Wang, Shuli Xu, Juntao Li +4

School of Computer Science and Technology, Soochow University · Department of Foundation Model, 2012 Labs, Huawei · College of Intelligence and Computing, Tianjin University

RL for Language Model ReasoningReinforcement LearningEfficient Language Model ReasoningOverthinking in Language Models
AskPDF
Mar 7, 2026

Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory

Reinforcement learning has achieved remarkable success in robot learning. However, under challenging exploration and contact-rich dynamics, early-stage training is frequently dominated by premature terminations such as collisions and falls. As a result, learning is overwhelmed by short-horizon, low-return trajectories, which hinder convergence and limit long-horizon exploration. To alleviate this issue, we propose a technique called Failure Episodic Memory Alert (FEMA). FEMA explicitly stores short-horizon failure experiences through an episodic memory module. During interactions, it retrieves similar failure experiences and prevents the robot from recurrently relapsing into unstable states, guiding the policy toward long-horizon trajectories with greater long-term value. FEMA can be combined easily with model-free reinforcement learning algorithms, and yields a substantial sample-efficiency improvement of 33.11% on MuJoCo tasks across several classical RL algorithms. Furthermore, integrating FEMA into a parallelized PPO training pipeline demonstrates its effectiveness on a real-world bipedal robot task.

Chenyang Miao

Xi’an Jiaotong University

Reinforcement LearningRL ControlRobotic RLData-Efficient Robot Learning
AskPDF
Mar 7, 2026

Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution Networks

Extreme weather events and cyberattacks can cause component failures and disrupt the operation of power distribution networks (DNs), during which reconfiguration and load shedding are often adopted for resilience enhancement. This study introduces a topology-aware graph reinforcement learning (RL) framework for outage management that embeds higher-order topological features of the DN into a graph-based RL model, enabling reconfiguration and load shedding to maximize energy supply while maintaining operational stability. Results on the modified IEEE 123-bus feeder across 300 diverse outage scenarios demonstrate that incorporating the topological data analysis (TDA) tool, persistence homology (PH), yields 9-18% higher cumulative rewards, up to 6% increase in power delivery, and 6-8% fewer voltage violations compared to a baseline graph-RL model. These findings highlight the potential of integrating RL with TDA to enable self-healing in DNs, facilitating fast, adaptive, and automated restoration.

Roshni Anna Jacob, Prithvi Poddar, Jaidev Goel +3

The University of Texas at Dallas, Richardson, TX, USA · University at Buffalo, Buffalo, NY, USA · Virginia Tech, Blacksburg, VA, USA

Power SystemsReinforcement Learning
AskPDF
Mar 6, 2026

Boosting deep Reinforcement Learning using pretraining with Logical Options

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans' ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based reinforcement learning agents without sacrificing the expressivity of deep policies. Our method, called Hybrid Hierarchical RL (H^2RL), introduces a logical option-based pretraining strategy to steer the learning policy away from short-term reward loops and toward goal-directed behavior while allowing the final policy to be refined via standard environment interaction. Empirically, we show that this approach consistently improves long-horizon decision-making and yields agents that outperform strong neural, symbolic, and neuro-symbolic baselines.

Zihan Ye, Phil Chau, Raban Emunds +5

CS Department, Technical University of Darmstadt, Germany · AIML Group · Hessian AI +2

Neuro-Symbolic RLReinforcement LearningHierarchical RL
AskPDF