Generalization in RL

RL: Reinforcement Learning

Ask about this topic

Overview

The field asks whether an agent can act effectively when goals, layouts, visual inputs, dynamics, or collaborators differ from training, a requirement for reliable deployment. Common approaches include domain randomization and exploration for broader state coverage, invariant or task-conditioned representations, meta-learning, curricula, reusable skills, and Bayesian or model-based transfer. Researchers evaluate these methods in settings such as Procgen, MuJoCo, MetaWorld, DeepMind Control, robotics, and language-based agents, using held-out tasks, environments, and visual or dynamics shifts. A central tension is that diversity and regularization can improve transfer but hinder learning or retention, while benchmark design and metrics can make apparent generalization gains hard to interpret.

Latest papers

CardsList

89 papers16 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

  1. Factorization Regret mediates compositional generalization in latent space

    Mar 28, 2026John SchwarczGeneralization in RLCompositional Representation Learning

    Edmond & Lily Safra Center for Brain Sciences (ELSC), The Hebrew University of Jerusalem

  2. From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments

    Mar 25, 2026Lijing Luo, Yiben Luo, Alexey Gorbatovski +2RL BenchmarksReinforcement Learning

    Sun Yat-sen University Shenzhen, China · Yancheng Institute of Technology Yancheng, China · Central University Moscow, Russia +1

  3. PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

    Mar 22, 2026Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang +9RL Post-TrainingRL for LLM Agents

    NVIDIA · UC Berkeley

  4. Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)

    Mar 18, 2026Nicola J. Müller, Moritz Oster, Isabel Valera +2Generalization in RLQ-Learning

    German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany · Saarland University, Saarland Informatics Campus, Saarbrücken, Germany · Center for European Research in Trusted Artificial Intelligence (CERTAIN)

  5. ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning

    Mar 16, 2026Issa Nakamura, Tomoya Yamanokuchi, Yuki Kadokawa +5Reinforcement LearningGoal-Conditioned RL

    I. Nakamura, T. Yamanokuchi, Y. Kadokawa, and T. Matsubara are with the Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan. · J. Qu, S. Otsubo, Y. Susumu, S. Miwa are with the Advanced Technology R&D Center, Mitsubishi Electric Corporation, Hyogo, Japan.

  6. Can RL Improve Generalization of LLM Agents? An Empirical Study

    Mar 12, 2026Zhiheng Xi, Xin Guo, Jiaqi Liu +11LLM AgentsRL for LLM Agents

    Fudan University · Shanghai Artificial Intelligence Laboratory · Meituan

  7. DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

    Mar 8, 2026Jinzhou Tang, Fan Feng, Minghao Fu +3World Model LearningWorld Models

    UC San Diego · Sun Yat-sen University

  8. Generalization in Online Reinforcement Learning for Mobile Agents

    Mar 8, 2026Li Gu, Zihuan Jiang, Zhixiang Chi +5RL for GUI AgentsMobile GUI Agents

    Mila – Québec AI Institute · Concordia University · University of Toronto +3

  9. Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

    Mar 6, 2026Ondřej Lukáš, Jihoon Shin, Emilia Rivas +6Generalization in RLAI Agent Evaluation

    Czech Technical University in Prague (CTU) · University of Texas at El Paso (UTEP) · Universidad Nacional de Cuyo (UNCUYO)

  10. Synthetic Monitoring Environments for Reinforcement Learning

    Mar 6, 2026Leonard Pleiss, Carolin Schmidt, Maximilian SchifferRL BenchmarksReinforcement Learning

    Technical University Munich Munich, 80331

  11. Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

    Mar 3, 2026Mohammadreza Nakheai, Aidan Scannell, Kevin Luck +1Representation LearningOffline RL

    Aalto University · Toyota Research Institute · Vrije Universiteit Amsterdam

  12. Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs

    Mar 2, 2026Shuangchun Gui, Suyu Liu, Xuehe Wang +1RL for Combinatorial OptimizationMulti-Task RL

    School of Computing and Information Systems, Singapore Management University, Singapore · Guangdong Laboratory of AI and Digital Economy, Shenzhen, Guangdong, China · School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, Guangdong, China

  13. Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries

    Feb 28, 2026Paul Nitschke, Shahriar TalebiSymmetry DiscoveryMeta-Reinforcement Learning

    P. Nitschke is with the Paulson School Of Engineering And Applied Sciences, Harvard University, Cambridge, US. · S. Talebi is with the UCLA Samueli School of Engineering and Applied Science, University of California, Los Angeles, US.

  14. Generalisation of RLHF under Reward Shift and Clipped KL Regularisation

    Feb 25, 2026Kenton Tang, Yuzhu Chen, Fengxiang HeRL from Human FeedbackGeneralization in RL

    University of Edinburgh · University of Science and Technology of China

  15. Sparse Masked Attention Policies for Reliable Generalization

    Feb 23, 2026Caroline Horsch, Laurens Engwegen, Max Weltevrede +2Reinforcement LearningGeneralization in RL

    Department of Intelligent Systems, Delft University of Technology, Delft, Netherlands.

  16. Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent

    Feb 23, 2026Björn Hoppmann, Christoph ScholzMeta-LearningMeta-Reinforcement Learning

  17. Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts

    Feb 22, 2026Toshihide Ubukata, Zhiyao Wang, Enhong Mu +2RL ExplorationGeneralization in RL

    Waseda University, Tokyo, 169-8050, Japan. · Osaka University, Japan. · Southwest University, China. +1

  18. Discovering Multiagent Learning Algorithms with Large Language Models

    Feb 18, 2026Zun Li, John Schultz, Daniel Hennes +1Counterfactual Regret MinimizationMulti-Agent Reinforcement Learning

    Google DeepMind

  19. Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking

    Feb 18, 2026Siyuan Wang, Lei Lei, Pranav Maheshwari +2RL BenchmarksReinforcement Learning

    College of Engineering, University of Guelph, Guelph, Ontario, Canada · College of Electrical Engineering and Computer Sciences, Ningbo University, Ningbo, 315211, China

  20. EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments

    Feb 18, 2026Sushant Mehta, Logan Ritchie, Suhaas Garre +3LLM Agent TrainingRL for LLM Agents

    Surge AI

  21. Contextual Intelligence The Next Leap for Reinforcement Learning

    Feb 17, 2026André BiedenkappContextual RLZero-Shot RL

    Albert-Ludwigs-Universität Freiburg, Germany

  22. PlatoLTL: Scaling LTL-Guided Multi-Task RL

    Jan 30, 2026Jacques Cloete, Mathias Jackermeier, Ioannis Havoutis +1RL for RoboticsConstrained RL

    Oxford Robotics Institute University of Oxford Oxford, United Kingdom · Department of Computer Science University of Oxford Oxford, United Kingdom

  23. KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

    Jan 20, 2026Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1RL BenchmarksReinforcement Learning

    1AXXX, Moscow, Russia · 2MIRAI, Moscow, Russia

  24. Meta-RL with Bayesian Linear Task Models

    Dec 24, 2025Jingyang You, Hanna KurniawatiRepresentation LearningReinforcement Learning

    School of Computing Australian National University

  25. RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

    Jul 21, 2025Lu Guo, Yixiang Shan, Zhengbang Zhu +5Offline RLGeneralization in RL

    School of Artificial Intelligence, Jilin University, Changchun, China · School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

  26. Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

    Apr 12, 2025Zhiyong WangMulti-Armed BanditsReinforcement Learning

    Department of Computer Science and Engineering, The Chinese University of Hong Kong

  27. A Generalist Hanabi Agent

    Mar 17, 2025Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond +3RL for Game AICooperative MARL

    Chandar Research Lab · Mila – Quebec AI Institute · Polytechnique Montréal +4

  28. Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

    Oct 4, 2024Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1Reinforcement LearningRL Exploration

    Delft University of Technology, Delft, The Netherlands

  29. Policy Learning with a Language Bottleneck

    May 7, 2024Megha Srivastava, Cedric Colas, Dorsa Sadigh +1Policy LearningLLM-Guided RL

    Stanford University · Massachusetts Institute of Technology Inria