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

1,767 papers195 papers in the last four weeks, down 8% on the four weeks before. 1.3% of all new papers.

Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
May 6, 2026Xiyan Fu, Wei LiuReinforcement Learning RL for Generative Models
Nanyang Technological University · Independent Researcher
A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs
May 6, 2026Erel Shtossel, Alicia Vidler, Uri Shaham +1Non-Stationary RL Reinforcement Learning
Bar Ilan University Ramat Gan, Israel
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
May 6, 2026Lirui Luo, Guoxi Zhang, Hongming Xu +2Loss of Plasticity Reinforcement Learning
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
Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
May 6, 2026Akiyoshi Tomihari, Issei SatoReinforcement Learning KL-Regularized RL
Department of Computer Science, The University of Tokyo
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
May 6, 2026Keyu Chen, Nanfei Ye, Yida Wang +4Reinforcement Learning Autonomous Driving Planning
School of Vehicle and Mobility, Tsinghua University · Li Auto Inc
Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
May 6, 2026Lingzhe Zhang, Tong Jia, Yunpeng Zhai +6Reinforcement Learning RL Fine-Tuning
Peking University, Beijing, China · Alibaba Group, China · University of Illinois Chicago, United States
Extending Differential Temporal Difference Methods for Episodic Problems
May 6, 2026Kris De Asis, Mohamed Elsayed, Jiamin HeEpisodic RL Reinforcement Learning
1Openmind Research Institute · Department of Computing Science, University of Alberta, Canada · 3Alberta Machine Intelligence Institute (Amii)
Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies
May 5, 2026Senne Deproost, Mehrdad Asadi, Ann NowéReinforcement Learning Interpretability in RL
aVrije Universiteit Brussel · bFlanders Make
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes
May 5, 2026Cyrille Kone, Kevin JamiesonThompson Sampling Markov Decision Processes
Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189-CRIStAL, F-59000 Lille, France · University of Washington, Seattle, USA
Discovering Reinforcement Learning Interfaces with Large Language Models
May 5, 2026Akshat Singh Jaswal, Ashish Baghel, Paras ChopraReinforcement Learning LLM-Guided RL
Lossfunk
Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning
May 4, 2026Matthew Schlegel, Volodymyr Tkachuk, Adam White +1Reinforcement Learning Recurrent Neural Networks
University of Alberta
Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
May 4, 2026Lingxiao Kong, Cong Yang, Oya Deniz Beyan +1RL for Robotics Reinforcement Learning
Fraunhofer Institute for Applied Information Technology FIT, Germany · Soochow University, China · University of Cologne, Germany +1
Recurrent Deep Reinforcement Learning for Chemotherapy Control under Partial Observability
May 4, 2026Firas Mohamed Elamine Kiram, Imane Youkana, Rachida Saouli +2Reinforcement Learning Healthcare
Dept. of Information Engineering University of Padova Padova, Italy · LINFI Lab, Dept. of Computer Science University of Biskra Biskra, Algeria
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
May 4, 2026Yao Shu, Chenxing Wei, Hongbin Lin +2Supervised Fine-Tuning Reinforcement Learning
Binary Rewards and Reinforcement Learning: Fundamental Challenges
May 4, 2026Marc DymetmanReinforcement Learning KL-Regularized RL
∗Scientific Consultant
T $^2$ PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
May 4, 2026Haixin Wang, Hejie Cui, Chenwei Zhang +7RL for LLM Agents Reinforcement Learning
University of California, Los Angeles · 2Amazon.com Inc.
Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
May 4, 2026Wenyi Wu, Sibo Zhu, Kun Zhou +1Reinforcement Learning Multi-Agent Collaboration
University of California, San Diego
Combining Trained Models in Reinforcement Learning
May 4, 2026Ujjwal Patil, Javad GhofraniReinforcement Learning Knowledge Distillation
Department of Computer Science Hochschule Bonn-Rhein-Sieg (H-BRS) Sankt Augustin, Germany
Bridging the Gap Between Average and Discounted TD Learning
May 3, 2026Haoxing Tian, Zaiwei Chen, Ioannis Ch. Paschalidis +1Reinforcement Learning Average-Reward RL
Department of Electrical and Computer Engineering Boston University · Edwardson School of Industrial Engineering Purdue University
Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning
May 3, 2026Arash Ahmadi, Sarah Sharif, Yaser +1Reinforcement Learning Large Language Model-Guided Optimization
Mike · School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019 USA · Intelligent Neuromorphic and Quantum Understanding for Innovative Research and Engineering (INQUIRE) Laboratory, University of Oklahoma, Norman, OK, USA
AdamO: A Collapse-Suppressed Optimizer for Offline RL
May 3, 2026Nan Qiao, Sheng Yue, Shuning Wang +1Reinforcement Learning Orthogonal Optimization
1Tsinghua University, China · 2Central South University, China · 3Sun Yat-sen University, China
MOIRA: Policy Memory and Belief Revision for Language-Model Agents in Non-Stationary Pair Trading
May 3, 2026Polydoros Giannouris, Yuechen Jiang, Lingfei Qian +5Reinforcement Learning Hierarchical RL
The University of Manchester Manchester, UK · The Fin AI USA · Harvard University Cambridge, MA, USA +1
Quality-Aware Exploration Budget Allocation for Cooperative Multi-Agent Reinforcement Learning
May 3, 2026Dahyun Oh, Minhyuk Yoon, H. Jin KimMulti-Agent Coordination Intrinsic Reward Methods
Department of Aerospace Engineering, Seoul National University, Seoul, Republic of Korea
Remote Action Generation: Remote Control with Minimal Communication
May 3, 2026Szymon Kobus, Deniz GündüzRL Control Reinforcement Learning
Electrical and Electronic Engineering Imperial College London
Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards
May 3, 2026Rudray Dave, Vedang Dubey, Smit Deoghare +1Reinforcement Learning RL for Language Model Reasoning
Department of Artificial Intelligence Sardar Vallabhbhai National Institute of Technology Surat, India
MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning
May 3, 2026Haohan Yu, Jinmiao Cong, Shengzhi Wang +2Multi-Agent Coordination Intrinsic Reward Methods
1Dalian University of Technology · 2Microsoft, Beijing, China
Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
May 3, 2026Tian Xu, Zhilong Zhang, Zexuan Chen +3Reinforcement Learning Adversarial Imitation Learning
National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University · School of Mathematics, Nanjing University
TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning
May 3, 2026Pritam Mishra, Coloma Ballester, Dimosthenis KaratzasReinforcement Learning Video Summarization
Universitat Pompeu Fabra, Barcelona, Spain · Universitat Autònoma de Barcelona, Barcelona, Spain
MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
May 2, 2026Yin Zhang, Jiaxuan Zhao, Zonghan Wu +5VLM Reasoning Vision-Language Models
School of Mathematics, Tianjin University, Tianjin, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · Shanghai Advanced Institute of Finance (SAIFS), East China Normal University, Shanghai, China +4
PACE: Parameter Change for Unsupervised Environment Design
May 2, 2026Fang Yuan, Quanjun Yin, Siqi Shen +5Reinforcement Learning
College of Systems Engineering, National University of Defense Technology, Changsha, China · Test Center, National University of Defense Technology, Xi’an, China · State Key Laboratory of Digital Intelligent Modeling and Simulation, Changsha, China +2

May 6, 2026J/K move · Enter open · S save

Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization

Xiyan Fu, Wei Liu

Nanyang Technological University · Independent Researcher

Reinforcement Learning RL for Generative Models RL Fine-Tuning Compositional Generalization

Open paper AskPDF arXiv

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs. This token-level training paradigm fails to capture the global compositional structure required for generalizing to unseen combinations. In this work, we investigate whether compositional generalization can instead be improved through outcome-level reinforcement learning. We adopt Group Relative Policy Optimization to optimize models based on feedback on their final outputs. Within this framework, we explore both a simple binary outcome reward and a composite reward that provides additional composition feedback. Experiments on multiple compositional benchmarks show that reinforcement learning improves compositional generalization compared to supervised fine-tuning. Further analysis reveals that supervised models tend to overfit frequent training compositions, whereas reinforcement learning improves compositional generalization by reshaping the output distribution, particularly for more complex composition types.