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.

Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow
Feb 16, 2026Minh NguyenReinforcement Learning Continuous-Time RL
Google · University of Texas at Austin
Calculating Mutual Information between a Reward Maximizer and its Environment
Feb 13, 2026Alfred Harwood, Jose Faustino, Alex AltairMarkov Decision Processes Reinforcement Learning
1Dovetail Research · University of Sao Paulo
TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction
Feb 12, 2026Yongyao Wang, Ziqi Miao, Lu Yang +4In-Context Example Selection Reinforcement Learning
Gaoling School of Artificial Intelligence, Renmin University of China · Shanghai AI Laboratory
Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning
Feb 12, 2026Xuan Yu, Xu Wang, Rui Zhu +2Reinforcement Learning Generative Flow Networks
University of Science and Technology of China (USTC), Hefei, China · Suzhou Institute for Advanced Research, USTC, Suzhou, China · State Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei, China
Can We Really Learn One Representation to Optimize All Rewards?
Feb 11, 2026Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin EysenbachZero-Shot RL Representation Learning
Princeton University
Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT
Feb 11, 2026Jiacheng Wang, Zhijie Liu, Ping Jian +4Supervised Fine-Tuning Reinforcement Learning
Beijing Institute of Technology, Beijing, China · Tsinghua University, Beijing, China
Reinforcement learning with an expectile-based objective
Feb 10, 2026Shrey Rakeshkumar Patel, Sumedh Gupte, Soumen Pachal +2Reinforcement Learning Risk-Sensitive RL
Indian Institute of Technology Madras · TCS Research, India
SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
Feb 9, 2026Shae McFadden, Myles Foley, Elizabeth Bates +5Reinforcement Learning Cybersecurity
King’s College London · The Alan Turing Institute · University College London +3
Combining Constrained Sampling and Reinforcement Learning for Manipulation
Feb 9, 2026Marc Toussaint, Cornelius V. Braun, Armand Jordana +5Reinforcement Learning Non-Prehensile Manipulation
Technische Universität Berlin · Robotics Institute Germany · LAAS-CNRS +1
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
Feb 8, 2026Lior Cohen, Ofir Nabati, Kaixin Wang +2Reinforcement Learning World Model Learning
Technion · Microsoft Research
Process Rewards for Outcome-Guided Reasoning Steps in LLM Reinforcement Learning
Feb 8, 2026Mohammad Rezaei, Jens Lehmann, Sahar VahdatiLLM Mathematical Reasoning Reinforcement Learning
Faculty of Computer Science, Technical University of Dresden, Dresden, Germany · Amazon Science · Technical University of Dresden, Dresden, Germany +1
USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
Feb 8, 2026Hongzhi Zang, Shu'ang Yu, Hao Lin +14Robot Policy Learning Reinforcement Learning
Tsinghua University · Shanghai AI Laboratory · Infinigence AI +3
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
Feb 8, 2026Xian Wu, Kaijie Zhu, Ying Zhang +2Reinforcement Learning Process Reward Models
Meta AI · Department of Computer Science, University of California, Santa Barbara · Independent Researcher +1
A Behavior-first approach to Multi-Intention Inverse Reinforcement Learning
Feb 7, 2026Antonio Mone, Frans A. Oliehoek, Luciano Cavalcante SiebertReinforcement Learning
Delft University of Technology, the Netherlands
Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions
Feb 7, 2026Yicheng Yang, Ruijiao Li, Lifeng Wang +7Reinforcement Learning Robotic RL
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Feb 6, 2026Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov +4Reinforcement Learning RL for Language Model Reasoning
T-Tech · Saint Petersburg Electrotechnical University “LETI”
The impact of temporal resampling on the safety of clinical reinforcement learning: A simulated trial
Feb 6, 2026Thomas Frost, Hrisheekesh Vaidya, Steve HarrisReinforcement Learning Offline RL
University College London, London, United Kingdom · University College London Hospitals NHS Foundation Trust, London, United Kingdom
Difficulty-Estimated Policy Optimization
Feb 6, 2026Yu Zhao, Fan Jiang, Tianle Liu +5RL for Language Model Reasoning Policy Optimization
Alibaba International Digital Commerce · School of Software Technology, Dalian University of Technology Dalian, China
Flow Matching for Offline Reinforcement Learning with Discrete Actions
Feb 5, 2026Fairoz Nower Khan, Nabuat Zaman Nahim, Ruiquan Huang +2Markov Chains Reinforcement Learning
Department of Computer Science, University of Kentucky · Department of Computing and Information Sciences, Rochester Institute of Technology
On the Role of Computation in Reinforcement Learning
Feb 5, 2026Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko +1Reinforcement Learning Model-Free RL
Department of Computer Science, Princeton University · Warsaw University of Technology · University of Warsaw +2
Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
Feb 3, 2026Jinwoo Choi, Sang-Hyun Lee, Seung-Woo SeoReinforcement Learning Hierarchical RL
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea · Department of Automotive Engineering, Ajou University, Gyeonggi-do, South Korea
VLM-Guided Experience Replay
Feb 2, 2026Elad Sharony, Tom Jurgenson, Orr Krupnik +2Reinforcement Learning Prioritized Experience Replay
Technion · ForSight Robotics · Nvidia Research
Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
Feb 2, 2026Mingyi Li, Taira Tsuchiya, Kenji YamanishiRegret Minimization in RL Markov Decision Processes
Department of Mathematical Informatics, The University of Tokyo, Tokyo, Japan · RIKEN AIP, Tokyo, Japan
MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI
Jan 30, 2026Zhengyi Lu, Ming Lu, Chongyu Qu +11Magnetic Resonance Imaging Accelerated MRI Reconstruction
Vanderbilt University, Nashville, TN, USA 37215 · Vanderbilt University Medical Center, Nashville, TN, USA 37232 · Oak Ridge National Laboratory, Oak Ridge, TN, USA 37831
Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
Jan 30, 2026Mathieu Petitbois, Rémy Portelas, Sylvain LamprierReinforcement Learning Offline RL
Ubisoft La Forge, Bordeaux, France · Université d’Angers, Angers, France
Emergence of Physical Intelligence via Controllable Information Production
Jan 30, 2026Tristan Shah, Stas TiomkinRobotic RL Reinforcement Learning
Department of Computer Science, Texas Tech University
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
Jan 29, 2026Abhijeet Sinha, Sundari Elango, Dianbo LiuReinforcement Learning Behavioral Diversity in RL
National University of Singapore, Singapore · IIT Madras, India
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
Jan 26, 2026Yibo Li, Zijie Lin, Ailin Deng +5Continual Learning for LLM Agents Reinforcement Learning
National University of Singapore, Singapore.
CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Jan 21, 2026Tianshi Xu, Yuteng Chen, Meng LiAgentic RL Reinforcement Learning
Peking University · NTU, Singapore
Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions
Jan 21, 2026Asim H. Gazi, Yongyi Guo, Daiqi Gao +3Non-Stationary RL Reinforcement Learning
Department of Computer Science, Harvard University · Department of Statistics, Harvard University · Department of Statistics, University of Wisconsin–Madison +2

Feb 16, 2026J/K move · Enter open · S save

Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow

Minh Nguyen

Google · University of Texas at Austin

Reinforcement Learning Continuous-Time RL RL Control Actor-Critic Methods

Open paper AskPDF arXiv

Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in this setting: as time gaps shrink, the

Q

-function collapses to the value function

V

, eliminating action ranking. Existing continuous-time methods reintroduce action information via an advantage-rate function

q

. However, they enforce optimality through complicated martingale losses or orthogonality constraints, which are sensitive to the choice of test processes. These approaches entangle

V

and

q

into a large, complex optimization problem that is difficult to train reliably. To address these limitations, we propose a novel decoupled continuous-time actor-critic algorithm with alternating updates:

q

is learned from diffusion generators on

V

, and

V

is updated via a Hamiltonian-based value flow that remains informative under infinitesimal time steps, where standard max/softmax backups fail. Theoretically, we prove rigorous convergence via new probabilistic arguments, sidestepping the challenge that generator-based Hamiltonians lack Bellman-style contraction under the sup-norm. Empirically, our method outperforms prior continuous-time and leading discrete-time baselines across challenging continuous-control benchmarks and a real-world trading task, achieving 21% profit over a single quarter

-

nearly doubling the second-best method.