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.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Apr 13, 2026Yang Liu, Enxi Wang, Yufei Gao +6RL for Language Models Reinforcement Learning
Fudan University · Shanghai Innovation Institute
NimbusGuard: A Novel Framework for Proactive Kubernetes Autoscaling Using Deep Q-Networks
Apr 13, 2026Chamath Wanigasooriya, Indrajith EkanayakeCloud Computing Reinforcement Learning
Department of Computer Science, Informatics Institute of Technology, Sri Lanka
When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies
Apr 13, 2026Zhengzhe YangLLM-Guided RL Reinforcement Learning
Independent Researcher
Robust Adversarial Policy Optimization Under Dynamics Uncertainty
Apr 13, 2026Mintae Kim, Koushil SreenathAdversarial MARL Reinforcement Learning
Hybrid Robotics, UC Berkeley Berkeley, CA 94720, USA
ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
Apr 13, 2026Xiaotian Qiu, Lukai Chen, Jinhao Li +3RL for Flow Matching Models Flow-Based Policy Learning
Zhejiang University, Hangzhou, China · Shanghai Innovation Institute · Shanghai Jiao Tong University, Shanghai, China +1
EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation
Apr 13, 2026Chongliu Jia, Yi Luo, Sipeng Han +5Evolutionary RL Portfolio Optimization
University of Connecticut · Xi’an University of Technology · Iowa State University +1
PokeRL: Reinforcement Learning for Pokemon Red
Apr 12, 2026Dheeraj Mudireddy, Sai PatibandlaRL for Game AI Reinforcement Learning
Texas A&M Institute of Data Science Texas A&M University College Station, USA · Dept. of Computer Science Texas A&M University College Station, USA
Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment
Apr 12, 2026Daniel J. Tan, Jayne Hui Zhen Chan, Kai Wen Hwang +3Reward Design for RL Reinforcement Learning
Institute of Data Science, National University of Singapore, Singapore · National University Hospital, Singapore · Saw Swee Hock School of Public Health, National University of Singapore, Singapore
Designing a double deep reinforcement learning selection tool for resilient demand prediction
Apr 12, 2026Bilel Abderrahmane Benziane, Benoit Lardeux, Ayoub Mcharek +1Model Selection Time Series Forecasting
DataLab, Generix Group, 8 Rue Simone IFF, 75012, Paris, France
Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards
Apr 12, 2026Huiming Zhang, Binghan Li, Wan Tian +1Information-Theoretic Generalization Bounds LLM Alignment
BUAA and BAIC-FBPC · BUAA · PKU +1
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
Apr 12, 2026Zikang Shan, Han Zhong, Liwei Wang +1RL for Language Models Reinforcement Learning
Peking University · Microsoft Research Asia · Shanghai Jiao Tong University
Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching
Apr 12, 2026Jiahuan Jin, Wenhao Zhao, Rong Qu +4Multi-Party Multi-Objective Optimization Multi-Objective Optimization
School of Computer Science, University of Nottingham Ningbo China, Ningbo, China. · School of Computer Science, University of Nottingham, Nottingham, UK. · Department of Computer Science, City University of Hong Kong, Hong Kong
Safety Guarantees in Zero-Shot Reinforcement Learning for Cascade Dynamical Systems
Apr 12, 2026Shima Rabiei, Sandipan Mishra, Santiago PaternainZero-Shot RL Safe RL
The authors are with the Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute. · The author is with the Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute.
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
Apr 11, 2026Yiming Huang, Zhenbo Shi, Xin-Cheng Wen +4Reinforcement Learning RL for Language Model Reasoning
Harbin Institute of Technology, Shenzhen · The Chinese University of Hong Kong · Peng Cheng Laboratory
Online Intention Prediction via Control-Informed Learning
Apr 10, 2026Tianyu Zhou, Zihao Liang, Zehui Lu +1Online Learning Reinforcement Learning
School of Aeronautics and Astronautics, Purdue University, IN 47907, USA · independent researcher
On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach
Apr 10, 2026Anas Hattay, Fred Ngole Mboula, Eric Gascard +1Cloud Computing Reinforcement Learning
CEA, List, Université Paris-Saclay, France · Université Grenoble Alpes, CNRS, Grenoble INP, G-SCOP, France
Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks
Apr 10, 2026Wen Qiu, Zhiqiang He, Wei Zhao +1UAV Communication Reinforcement Learning
Department of Information and Communication Engineering, Kitami Institute of Technology, Japan. · Graduate School of Informatics and Engineering, the University of Electro-Communications, Japan. · School of Computer Science and Technology, Anhui University of Technology, China. +1
WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning
Apr 10, 2026Mintae Kim, Koushil SreenathReinforcement Learning Sample-Efficient RL
Hybrid Robotics, UC Berkeley Berkeley, CA 94720, USA
HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation
Apr 10, 2026Chengjie Fan, Cong Pan, Zijian Liu +2Visual Navigation Robot Navigation
Nanjing University of Aeronautics and Astronautics, China Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, China
Building Better Environments for Autonomous Cyber Defence
Apr 9, 2026Chris Hicks, Elizabeth Bates, Shae McFadden +12Autonomous Cyber Defense Cybersecurity
The Alan Turing Institute · University College London · King’s College London +4
Artifacts as Memory Beyond the Agent Boundary
Apr 9, 2026John D. Martin, Fraser Mince, Esra'a Saleh +1Memory-Augmented Agents Reinforcement Learning
Openmind Research Institute · University of Alberta · Cohere Labs Community +3
Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains
Apr 9, 2026Haokai Ma, Lee Yan Zhen, Gang Yang +4RL for Language Models Reinforcement Learning
National University of Singapore, Singapore · Singapore Management University, Singapore
ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
Apr 9, 2026Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu RanaZero-Shot RL Zero-Shot Policy Transfer
Applied Artificial Intelligence Initiative, Deakin University, Waurn Ponds, Geelong · School of IT, Deakin University, Waurn Ponds, Geelong
On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics
Apr 9, 2026Ana María Gómez Ruiz, Thao Dang, Alexandre DonzéRL Control Reinforcement Learning
UGA · VERIMAG, Université Grenoble Alpes · VERIMAG - IMAG, CNRS, UGA +1
Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
Apr 9, 2026Chuzhan Hao, Wenfeng Feng, Guochao Jiang +3Agentic Search RL for Language Model Reasoning
Alibaba Cloud Computing
StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning
Apr 9, 2026Ivo NowakReinforcement Learning Distributional RL
HAW-Hamburg
Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
Apr 9, 2026Haruto Nagahisa, Kohei Matsumoto, Yuki Tomita +2Reinforcement Learning Mobile Robotics
Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan · Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
Apr 9, 2026Hao Gu, Hao Wang, Jiacheng Liu +9Reinforcement Learning RL Fine-Tuning
The Hong Kong University of Science and Technology · City University of Hong Kong · Zhejiang University
Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
Apr 9, 2026Pei-Xi Xie, Che-Yu Lin, Cheng-Lin YangReinforcement Learning LLM Mathematical Reasoning
CyCraft AI Lab, Taiwan
ReBound: Reset-Free Reinforcement Learning for Agile Driving via Reset-Aware Semi-Markov Bootstrapping
Apr 9, 2026Kohei Honda, Aiki Kada, Hirotaka HosogayaReinforcement Learning RL for Autonomous Driving
Department of Mechanical Systems Engineering, Nagoya University, Aichi, Japan · CyberAgent AI Lab, Tokyo, Japan

Apr 13, 2026J/K move · Enter open · S save

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Yang Liu, Enxi Wang, Yufei Gao, Weixin Zhang+5

Fudan University · Shanghai Innovation Institute

RL for Language Models Reinforcement Learning Reward Design for RL Behavioral Diversity in RL

Open paper AskPDF arXiv

Despite the success of reinforcement learning for large language models, a common failure mode is reduced sampling diversity, where the policy repeatedly generates similar erroneous behaviors. Classical entropy regularization encourages randomness under the current policy, but does not explicitly discourage recurrent failure patterns across rollouts. We propose MEDS, a Memory-Enhanced Dynamic reward Shaping framework that incorporates historical behavioral signals into reward design. By storing and leveraging intermediate model representations, we capture features of past rollouts and use density-based clustering to identify frequently recurring error patterns. Rollouts assigned to more prevalent error clusters are penalized more heavily, encouraging broader exploration while reducing repeated mistakes. Across five datasets and three base models, MEDS consistently improves average performance over existing baselines, achieving gains of up to 4.13 pass@1 points and 4.37 pass@128 points. Additional analyses using both LLM-based annotations and quantitative diversity metrics show that MEDS increases behavioral diversity during sampling.