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

1,742 papers237 papers in the last four weeks, up 46% on the four weeks before. 1.4% of all new papers.

SCARL: Sequence Confidence-Aligned Reinforcement Learning
Oct 29, 2026Zhenghong Ke, Jingbo Zhou, Hua WuReinforcement Learning RL for Language Model Reasoning
Baidu Frontier Research Department · Nanjing University
Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR
Oct 29, 2026Lang Chen, Zongxin Xu, Borui Wang +2Reinforcement Learning Token-Level Credit Assignment
Shenzhen University
Closing the Log Gap: Minimax-Optimal Regret for Episodic RL
Oct 29, 2026Guy Zamir, Victor Boone, Matthew Zurek +1Reinforcement Learning Regret Minimization in RL
Department of Computer Sciences, University of Wisconsin–Madison · IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France
Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information
Oct 29, 2026Daniel Strauss, Nikolaos Sotirakis, Zhenshan Bing +1Reinforcement Learning Memory-Augmented RL
Technical University of Munich · Nanjing University · Harbin Institute of Technology
Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence
Oct 29, 2026Chenxi Li, Yao Shu, Siyang Gao +2Multi-Objective Reinforcement Learning Reinforcement Learning
Harbin Institute of Technology, Harbin, Heilongjiang, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China · City University of Hong Kong, Hong Kong, China
Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents
Oct 29, 2026Yuxiang Chai, Quyu Kong, Panrong Tong +2RL for GUI Agents Reinforcement Learning
Alibaba Token Hub, Alibaba Group · MMLab, The Chinese University of Hong Kong
Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty
Oct 28, 2026Atin Chowdhury, Piyush JoshiReinforcement Learning Robust RL
Department of Computer Science and Engineering, Indian Institute of Information Technology, Sri City, Andhra Pradesh, India
Force-Driven Hook Disassembly via Constraint-Aware Object-Centric Reinforcement Learning
Oct 28, 2026Nadeen Elhadad, Takuya Kiyokawa, Kensuke HaradaRobotic Manipulation Reinforcement Learning
N. Elhadad, T. Kiyokawa, and K. Harada are with the Department of Systems Innovation, Graduate School of Engineering Science, The University of Osaka, 1-3 Machikaneyama, Toyonaka, Osaka, Japan. · K. Harada is with the Industrial Cyber-physical Systems Research Center, The National Institute of Advanced Industrial Science and Technology (AIST), 2-3-26 Aomi, Koto-ku, Tokyo, Japan.
CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization
Oct 28, 2026Zhiyuan Xiang, Xiang Deng, Wanjie Tao +3Robot Policy Learning Robot Skill Learning
Harbin Institute of Technology (Shenzhen) · Mashang Consumer Finance Co., Ltd. · Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
Learning from Relative Action Credit for Escaping Local Minima
Oct 27, 2026Giovanni Minelli, Giulio Turrisi, Lorenzo Amatucci +2Reinforcement Learning Robotic RL
Istituto Italiano di Tecnologia, Genova, Italy
EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning
Oct 27, 2026Sihan Yang, Weichen Bai, Ruichuan An +9Agentic RL Reinforcement Learning
PKU · XJTU · THU +3
Collective Dynamics of Self-Reinforcement: How Cross-Task Coupling Drives Policy Collapse in Unsupervised RLVR
Oct 27, 2026Peize DingRL for Language Models Reinforcement Learning
Columbia University, New York, NY, USA
Hyperparameter and Neural Architecture Search via Evolutionary Optimization for Reinforcement Learning: HPNAS-RL
Oct 27, 2026Nihal Acharya Adde, Hanno GottschalkNeural Architecture Search Reinforcement Learning
Volkswagen Group Innovation, Volkswagen AG, Berliner Ring 2, Wolfsburg, 38440, Lower Saxony, Germany. · Institute of Mathematics, TU Berlin, Straße des 17. Juni 136, Berlin, 10623, Berlin, Germany.
SetGRPO: Calibrating Grader-Induced Policy Optimization
Oct 27, 2026Jiale Huang, Zixu Li, Zhiwei Chen +3Reinforcement Learning Group Relative Policy Optimization
Shandong University · National University of Singapore
CoHARL: Co-Evolving Agent Policies and Executable Harnesses with Reinforcement Learning
Oct 27, 2026Jianwen Chen, Peng Xia, Kaide Zeng +5Agent Harness Optimization RL for LLM Agents
University of North Carolina at Chapel Hill · RIKEN · Cisco
CONCUR: Concordant Auxiliary Rewards for Multi-Task, Multi-Reward Reinforcement Learning
Oct 27, 2026Jixuan Leng, Si Si, Fei Wang +4Reinforcement Learning RL for Language Models
CMU · Google DeepMind · Google +1
Repulsive Population Policy Gradients for Behaviorally Diverse Reinforcement Learning
Oct 27, 2026Saeed Hedayatian, Harsh Shah, Celine Mneimneh +1Reinforcement Learning Behavioral Diversity in RL
Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, USA · Independent Researcher
Learning Multi-Phase Robot Loco-Manipulation via Phase-Conditioned Policy Optimization
Oct 26, 2026Simone Manni, Annika Wollschläger, Dario Bellicoso +4Robotic Loco-Manipulation Long-Horizon Robotic Manipulation
Robotic Systems Lab (RSL), ETH Zurich, Zurich, Switzerland. · Robotics and AI Institute (RAI), Zurich, Switzerland.
Jaxnasium: Embracing PyTrees For Any-Agent, Cross-Suite Reinforcement Learning
Oct 26, 2026Koen Ponse, Aske Plaat, Thomas M. MoerlandReinforcement Learning
Leiden Institute of Advanced Computer Science Leiden University
Causal DAG-Guided Reinforcement Learning for Long-Term Physical Activity Maintenance: Using Prior Data to Inform Future Deployment
Oct 26, 2026Xueqing Liu, Young Hyun Cho, Bhanu Teja Gullapalli +2Reinforcement Learning Long-Horizon RL
Harvard University · University of Michigan
Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
Oct 26, 2026Zhenshuo Zhang, Ruoxuan Xiong, Hongyang R. ZhangMulti-Objective Reinforcement Learning Reinforcement Learning
Northeastern University, Boston, MA · Emory University, Atlanta, GA
MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors
Oct 26, 2026Runchu Tian, Zaid Khan, Zun Wang +2RL for LLM Agents Reinforcement Learning
Department of Computer Science, University of North Carolina at Chapel Hill
When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing
Oct 26, 2026Lei Zhao, Zongheng Cao, Xinyu HuReinforcement Learning Fine-Grained Credit Assignment
University of Pennsylvania · Philo Labs
Enhancing Deep Reinforcement Learning for Robotic Motion Planning via Task Decomposition
Oct 26, 2026Yuanzhi He, Victor Romero-Cano, Jiayu Xu +2Reinforcement Learning Robotic RL
School of Computational and Mathematical Sciences Cardiff University, United Kingdom
InterQ-RL: Interaction-Aware Correction of Execution Mismatch in Quantized Agentic RL
Oct 26, 2026Yingbo Hao, Song Liu, Guanghua Yu +3Reinforcement Learning Agentic RL
South China University of Technology · Tencent
Improving Reasoning with Rollout Agreement for Group-Based Policy Optimization
Oct 26, 2026Sohyun Son, Yerim Hong, Jaeyun Park +1Reinforcement Learning RL for Language Model Reasoning
Kyung Hee University, Yongin, Republic of Korea
What Outcome RL Buys: Finishing, Reliability, Rarely Reach
Oct 26, 2026Shan YangReinforcement Learning RL for Language Model Reasoning
Individual Researcher.
Best Policy Tracking in Reinforcement Learning
Oct 25, 2026Judith Echevarrieta, Etor Arza, Aritz Pérez +1Reinforcement Learning RL Stability
Basque Center for Applied Mathematics
CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning
Oct 25, 2026Changxu Ni, Feiran You, Yongan Guo +5Safe RL Reinforcement Learning
Southeast University · The University of Hong Kong · Nanjing University of Posts and Telecommunications
Reinforcement Learning for Adaptive Crowd Flow Control Using Dynamic Barriers
Oct 25, 2026Alhanof Alolyan, He Wang, Amani AlonayzanRL Control Reinforcement Learning
Princess Nourah bint Abdulrahman University, Saudi Arabia · University College London, United Kingdom · Independent Researcher

Oct 29, 2026J/K move · Enter open · S save

SCARL: Sequence Confidence-Aligned Reinforcement Learning

Zhenghong Ke, Jingbo Zhou, Hua Wu

Baidu Frontier Research Department · Nanjing University

Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Confidence Estimation in Language Models

Open paper AskPDF arXiv

Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning by scoring sampled responses with a rule-based verifier and reinforcing those that pass. Where a classifier's training couples predicted probability to labels, nothing ties an RLVR policy's confidence in a response to its reward: aligned training would drive responses with the same advantage toward equal confidence, yet the advantage is blind to confidence. Under this sequence-confidence misalignment, a success the policy barely found earns the same update as one it produces with near certainty, and a confident error is corrected no harder than an exploratory one. We propose SCARL (Sequence Confidence-Aligned Reinforcement Learning), which reshapes, but never re-signs, each advantage with the alignment gap between the response's group-relative confidence and the outcome its advantage certifies, normalized into shares of each class's advantage budget. Misaligned samples absorb the force, responses with the same advantage are driven toward equal confidence, and repairing the misalignment doubles as a remedy for the entropy collapse that erodes exploration. SCARL provably reduces to its base estimator when a class's confidences agree, adds no extra passes and one hyperparameter. On Qwen3-4B-Base it lifts average Pass@32 by 2.4 points over DAPO and is best among nine compute-matched methods on both coverage and per-draw accuracy; applied unchanged across four estimators and four backbones, it improves 14 of 16 settings while preserving policy entropy and widening the confidence-correctness separation. Our code is available at https://github.com/kezhh163/scarl.