Reinforcement Learning

Also known as RL

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

1,750 papers237 papers in the last four weeks, up 46% on the four weeks before. 1.4% of all new papers.

An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
Apr 9, 2026Andreas Plesner, Francisco Guzmán, Anish AthalyeRL for Code Generation Reinforcement Learning
Handshake AI · ETH Zurich
RL-ASL: A Dynamic Listening Optimization for TSCH Networks Using Reinforcement Learning
Apr 8, 2026F. Fernando Jurado-Lasso, J. F. JuradoIndustrial Internet of Things Wireless Communications
independent researcher, based in Cali, Colombia · Department of Basic Science, Faculty of Engineering and Administration, Universidad Nacional de Colombia Sede Palmira, Palmira 763531, Colombia
Regret-Aware Policy Optimization: Environment-Level Memory for Replay Suppression under Delayed Harm
Apr 8, 2026Prakul Sunil HiremathReinforcement Learning Safe RL
Department of Computer Science and Engineering, VTU, Belagavi, India · Aliens on Earth (AoE) Autonomous Research Group, Belagavi, India
Robust Quadruped Locomotion via Evolutionary Reinforcement Learning
Apr 8, 2026Brian McAteer, Karl MasonEvolutionary RL Reinforcement Learning
School of Computer Science, College of Science and Engineering, University of Galway, Galway, Ireland
Predictive Representations for Skill Transfer in Reinforcement Learning
Apr 8, 2026Ruben Vereecken, Luke Dickens, Alessandra RussoTransfer Learning in RL Predictive State Representations
Computer Science, Imperial College, UK · Information Studies, UCL, UK
Reinforcement Learning with Reward Machines for Sleep Control in Mobile Networks
Apr 8, 2026Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis +2Wireless Communications Reinforcement Learning
Department of Computer and Information Science, Linköping University, Linköping, Sweden · Ericsson Research
POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP
Apr 8, 2026Jiyun Won, Heemin Yang, Woohyeok Kim +2Reinforcement Learning
POSTECH CSE1 · POSTECH GSAI2
Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems
Apr 8, 2026Charbel Bou Chaaya, Mehdi BennisEquivariant Policy Learning Reinforcement Learning
The authors are with the Centre for Wireless Communications, University of Oulu, Finland
Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem
Apr 8, 2026Hyukjun Yang, Han-Dong Lim, Donghwan LeeFunction Approximation in RL Markov Decision Processes
the Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141, South Korea
Value Mirror Descent for Reinforcement Learning
Apr 7, 2026Zhichao Jia, Guanghui LanMarkov Decision Processes Reinforcement Learning
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 30332.
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
Apr 7, 2026Jingbo Sun, Qichao Zhang, Songjun Tu +5Unsupervised RL Reinforcement Learning
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory · School of Artificial Intelligence, University of Chinese A
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
Apr 7, 2026Shuai Zhen, Yanhua Yu, Ruopei Guo +2RL for LLM Agents Reinforcement Learning
Beijing University of Posts and Telecommunications · China Mobile Group Design Institute Co., Ltd · Singapore Management University
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning
Apr 7, 2026Xiaolong Wei, Zerun Zhu, Simin Niu +9Text Generation RL for Language Models
Beihang University · Baidu Inc. · Renmin University of China
Vehicle-as-Prompt: A Unified Deep Reinforcement Learning Framework for Heterogeneous Fleet Vehicle Routing Problem
Apr 6, 2026Shihong Huang, Shengjie Wang, Lei Gao +4Vehicle Routing RL for Combinatorial Optimization
Polytechnic Institute, Zhejiang University, 310015, Hangzhou, China · S.F. Technology Co., Ltd., 518054, Shenzhen, China · School of Management, Zhejiang University, 310058, Hangzhou, China
Cross-fitted Proximal Learning for Model-Based Reinforcement Learning
Apr 6, 2026Nishanth Venkatesh, Andreas A. MalikopoulosCross-Fitting Reinforcement Learning
Department of Systems Engineering, Cornell University, Ithaca, NY, USA · Applied Mathematics, Systems Engineering, Mechanical Engineering, Electrical & Computer Engineering, and School of Civil & Environmental Engineering, Cornell University, Ithaca, NY, USA
Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving
Apr 6, 2026Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou +3Reinforcement Learning Spiking Neural Networks
Electrical and Computer Engineering Department, Drexel University, Philadelphia, USA
Stratifying Reinforcement Learning with Signal Temporal Logic
Apr 6, 2026Justin Curry, Alberto SperanzonSignal Temporal Logic Reinforcement Learning
University at Albany, State University of New York, Department of Mathematics and Statistics, 1400 Washington Ave., Albany, NY 12202 USA · Lockheed Martin, Advanced Technology Labs, 1303 Corporate Center Dr, Eagan, MN 55121 USA
Analyzing Symbolic Properties for DRL Agents in Systems and Networking
Apr 6, 2026Mohammad Zangooei, Jannis Weil, Amr Rizk +2Reinforcement Learning Neural Network Verification
University of Waterloo, Waterloo, Canada · Leibniz University Hannover, Hannover, Germany
Selecting Decision-Relevant Concepts in Reinforcement Learning
Apr 6, 2026Naveen Raman, Stephanie Milani, Fei FangReinforcement Learning Interpretability in RL
Carnegie Mellon University · New York University
On the "Causality" Step in Policy Gradient Derivations: A Pedagogical Reconciliation of Full Return and Reward-to-Go
Apr 6, 2026Nima H. SiboniPolicy Gradient Methods Reinforcement Learning
Juna.ai, Kastanienallee 32, 10435 Berlin
Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions
Apr 6, 2026Daniel BlochNon-Markovian RL Reinforcement Learning
UNIVERSITY OF PARIS 6 & VINUNIVERSITY · Visting Professor at the College of Engineering and Computer Science, VinUniversity, Hanoi.
From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism
Apr 6, 2026Zhuohao Yu, Zhiwei Steven Wu, Adam BlockReward Hacking Reward Over-Optimization
Carnegie Mellon University · Columbia University
Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications
Apr 6, 2026Zequn Chen, Wesley J. MarreroReinforcement Learning Distributional RL
Thayer School of Engineering, Dartmouth College
Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization
Apr 5, 2026Soham Bonnerjee, Zhipeng Lou, Wei Biao WuPolyak-Ruppert Averaging Q-Learning
Department of Statistics, University of Chicago · Department of Mathematics, University of California, San Diego
Investigating the Impact of Subgraph Social Structure Preference on the Strategic Behavior of Networked Mixed-Motive Learning Agents
Apr 4, 2026Xinqi Gao, Mario VentrescaMulti-Agent Systems Multi-Agent Reinforcement Learning
Xinqi Gao is with the Department of Industrial Engineering, Purdue University, West Lafayette, IN 47906, USA · Mario Ventresca is with the Department of Industrial Engineering, Purdue University, West Lafayette, IN 47906, USA
Delayed homomorphic reinforcement learning for environments with delayed feedback
Apr 4, 2026Jongsoo Lee, Jangwon Kim, Soohee HanDelayed RL Reinforcement Learning
Department of Convergence IT Engineering, POSTECH, Pohang, 37673, South Korea · Department of Electrical Engineering, POSTECH, Pohang, 37673, South Korea
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
Apr 3, 2026Wachiravit Modecrua, Krittanon Kaewtawee, Krittin Pachtrachai +1Multi-Turn RL RL for Tool Use
Amity Research and Application Center (ARAC)
Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards
Apr 3, 2026Matthew Hwang, Yubin Liu, Ryo Hakoda +1Quadruped Locomotion Terrain-Aware Robot Locomotion
University of Tokyo, Japan
When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning
Apr 2, 2026Juarez Monteiro, Nathan Gavenski, Gianlucca Zuin +1Uncertainty Estimation in RL Reinforcement Learning
Kunumi Institute Belo Horizonte, MG, Brazil · King’s College London London, England, UK
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Apr 2, 2026Yuhang Wu, Xiangqing Shen, Fanfan Wang +4Retrieval-Augmented Generation Reinforcement Learning
School of Computer Science and Engineering, Nanjing University of Science and Technology, China · School of Intelligence Science and Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China

Apr 9, 2026J/K move · Enter open · S save

An Imperfect Verifier is Good Enough: Learning with Noisy Rewards

Andreas Plesner, Francisco Guzmán, Anish Athalye

Handshake AI · ETH Zurich

RL for Code Generation Reinforcement Learning Reinforcement Learning with Verifiable Rewards RL Post-Training

Open paper AskPDF arXiv

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used for post-training Large Language Models, but practical verifiers can make errors. We study how the rate and structure of reward noise affect RLVR in code generation, with a preliminary scientific-reasoning check. In multi-seed Qwen3 8B experiments on MBPP, mean validation reward over two fixed late evaluations is within 1 percentage point of the clean baseline at the tested resampled group-rollout noise rates through 20%, and within about 2 points at 30%. Confidence intervals allow larger losses; these point estimates do not establish a general tolerance threshold. We also examine full-program pass@k, four controlled noise structures, two model-based verifiers, and policy models from three families spanning 4B-9B parameters. We derive conditional advantage distributions for symmetric and asymmetric group noise, including retained format penalties, and show why clipping limits simple gradient-scaling arguments. The analysis identifies information preserved by whole-group corruption and limits on interpreting our asymmetric sweep as a precision-recall comparison. Overall, the results indicate that imperfect verification can support effective RLVR in the tested settings, while aggregate error rates alone do not characterize the learning signal.