Model-Based RL

RL: Reinforcement Learning

Overview

Model-based reinforcement learning studies how agents can learn or use a model of how actions change the environment, then plan with that model to improve decisions and reduce costly interaction. Common approaches include latent world models that predict future states, Dyna-style learning from imagined rollouts, and model-predictive control or tree search; Bayesian models and ensembles help represent uncertainty, while control barriers and other safety methods constrain actions. Methods are tested on suites such as DeepMind Control, MuJoCo, Atari, and D4RL, as well as robotic manipulation, autonomous driving, and other physical systems, alongside theoretical work on regret and sample complexity. The central tension is that imagined experience can make learning more efficient, but model errors may accumulate over long horizons or be exploited by the policy, so reliable uncertainty estimates, safe planning, and transfer to real systems remain open challenges.

Latest papers

CardsList

273 papers29 papers in the last four weeks, down 12% on the four weeks before. 0.2% of all new papers.

  1. Lyapunov-Inspired Sustained Balance on Dynamically Responsive Supports

    Nov 17, 2026Changyan Li, Guiyin Tian, Jing Xia +1Robotic ControlLyapunov-Based Control

  2. Towards Optimism-Pessimism Trade-off in Model-based Offline-to-Online Reinforcement Learning

    Nov 17, 2026Guochen Zhou, Yijun Yang, Qiqi Duan +6Reinforcement LearningOffline-To-Online RL

  3. Adaptive Memory for Online Reinforcement Learning under Sparse Model Changes

    Nov 16, 2026Sreejeet Maity, Sukanya Modak, Leonardo F. TosoNon-Stationary RLadaptive reinforcement learning

  4. Warm Starting Neural Dynamics Models From Few Jacobian Samples

    Nov 16, 2026Maxime Rochkoulets, Joppe De Jonghe, Mariya IshtevaModel-Based RLSample-Efficient RL

  5. XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a Minute

    Nov 16, 2026Nico Bohlinger, Jan PetersHumanoid Motion TrackingHumanoid Robot Locomotion

  6. Bellman Residual Bracketing: Resolving the Sample Complexity of Discounted and Average-Reward RL

    Nov 14, 2026Matthew Zurek, Yudong ChenReinforcement LearningSample-Efficient RL

  7. Latent Imagination for Parameterized Action Spaces

    Nov 11, 2026Atahan Cilan, İhsan Mert Muhacıroğlu, Ümit Can BekarReinforcement LearningHybrid Action Space RL

  8. FOE-Dreamer: Deployment-Efficient Learning of Cyber Defense Policies in Operational Networks

    Nov 11, 2026Yinuo Du, Christopher KiekintveldAutonomous Cyber DefenseSample-Efficient RL

  9. Koopman Model-Based Reinforcement Learning

    Nov 10, 2026Wenjian Hao, Paulo C. Heredia, Shaoshuai MouModel-Based RLRobotic Control

  10. Audited Gradients, Anchored Policies: Model-Based Reinforcement Learning for Efficient Flow Control

    Nov 9, 2026Ruige Kong, Stefania FrescaModel-Based RLSurrogate-Assisted Optimization

  11. Building World Models from Intrinsic Motivation

    Nov 9, 2026Reece Keller, Declan Kutscher, Xaq Pitkow +1Intrinsic MotivationWorld Model Learning

  12. DreamLander: A 6-DOF World Model based Reinforcement Learning Planetary Lander

    Nov 9, 2026George Nehma, Patrick Quinn, Madhur Tiwari +1RL ControlReinforcement Learning

  13. Learning to Act with World Models by Valuing What Comes Next

    Nov 9, 2026Chenghao Gao, Zhi Zhang, Dian Jin +2Model-Based RLSparse-Reward RL

  14. Reinforcement Learning based control of Cancer Chemotherapy treatments

    Nov 6, 2026Jayakody Kankanamalage Chamani ShiranthikaRL ControlOncology

  15. Encoding Memory in World Models with Test-Time Model-Based Reinforcement Learning

    Nov 6, 2026Maxime Burchi, Fayaz Ali Dharejo, Radu TimofteModel-Based RLMemory-Augmented RL

  16. TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework

    Nov 6, 2026Luzhan Yuan, Chao Mi, Xiahao Shi +6Automated BiddingReal-Time Bidding

  17. World Models Need Not Be Right to Rank Policies Right: Relative Bounds and Audit Limits

    Oct 31, 2026Ahanaf Hasan Ariq, Hasaan AhmadReinforcement LearningPolicy Evaluation

  18. Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective

    Oct 30, 2026Yuxin Chen, Yuejie Chi, Jianqing Fan +3Sample-Efficient RLModel-Based RL

  19. Density-Guided Bootstrap Boundaries for Latent World-Model Reinforcement Learning

    Oct 29, 2026Shashank Gupta, Pilhwa LeeModel-Based RLLatent World Models

  20. Closing the Log Gap: Minimax-Optimal Regret for Episodic RL

    Oct 29, 2026Guy Zamir, Victor Boone, Matthew Zurek +1Episodic RLReinforcement Learning

  21. Bayesian Offline Multi-Agent Reinforcement Learning with Latent World Models

    Oct 29, 2026Xi Xiong, Lu Liu, Yiming Li +1Offline MARLModel-Based RL

  22. Generating Critic-Guided Synthetic Experience in Latent World Models

    Oct 29, 2026Jorge de Freitas, Christos Ziakas, Alessandra RussoModel-Based RLOffline RL

  23. Vision-Language Agents Can Learn in Their Own Latent Worlds

    Oct 27, 2026Haoxi Li, Sikai Bai, Jianfei Ma +5RL for VLMsWorld Models for VLA Models

  24. Frequency-Uniform Log-Regret Reinforcement Learning for Diffusions

    Oct 27, 2026Jose Blanchet, Lutong Hao, Renyuan Xufitted q-iterationRegret Minimization in RL

  25. Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

    Oct 26, 2026Jonathan DeCastro, Thomas Balch, Emily Sumner +9Shared AutonomyHuman-in-the-Loop AI

  26. HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model

    Oct 25, 2026Chao Chen, Zhenrong Wang, Jilong Wang +4Robot Policy AdaptationHumanoid Motion Tracking

  27. Reinforcement Learning with Multi-Step Transition Predictions: A Bellman Theory

    Oct 23, 2026Chenbei Lu, Zaiwei Chen, Tongxin Li +2Reinforcement LearningModel-Based RL