Model-Based RL

RL: Reinforcement Learning

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

245 papers32 papers in the last four weeks, up 10% on the four weeks before. 0.2% of all new papers.

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
Mar 18, 2026Naoki Morihira, Amal Nahar, Kartik Bharadwaj +3Model-Based RL World Model Learning
Honda R&D Co., Ltd. · The University of Tokyo · RIKEN AIP
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
Mar 16, 2026Jacob Levy, Tyler Westenbroek, Kevin Huang +6World Models for Robotics Robot Policy Adaptation
University of Texas at Austin · University of Washington · FieldAI
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
Mar 13, 2026Ruicheng Zhang, Guangyu Chen, Zunnan Xu +5Embodied World Models World Models
Tsinghua University · X Square Robot · HKUST
ARROW: Augmented Replay for RObust World models
Mar 12, 2026Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst +3Continual RL Replay-Based Continual Learning
Department of Information Systems, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU) · Department of Data Science & AI, Faculty of Information Technology, Monash University · School of Computer Science and Engineering, Faculty of Engineering, University of New South Wales, Sydney
ResWM: Residual-Action World Model for Visual RL
Mar 11, 2026Jseen Zhang, Gabriel Adineera, Jinzhou Tan +1Model-Based RL World Model Learning
University of California, San Diego USA · Texas A&M University-Commerce USA
Integrating Lagrangian Neural Networks into the Dyna Framework for Reinforcement Learning
Mar 9, 2026Shreya Das, Kundan Kumar, Muhammad Iqbal +4Lagrangian Neural Networks Model-Based RL
Department of Electrical Engineering and Automation, Aalto University, Finland · VTT Technical Research Centre of Finland · Department of Computer Science, University of Helsinki, Finland +1
Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
Mar 9, 2026Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu +3Offline RL Model-Based RL
CityUHK · Tencent · UChicago +1
Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
Mar 8, 2026Yi Tian, Kaiqing Zhang, Russ Tedrake +1Linear Quadratic Regulator State Representation Learning
Massachusetts Institute of Technology · University of Maryland, College Park · Technical University Munich
Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving
Mar 7, 2026Jiazhuo Li, Linjiang Cao, Qi Liu +1World Models for Autonomous Driving World Model Learning
Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
Mar 7, 2026Michael Hauri, Friedemann ZenkeWorld Model Learning World Models
Friedrich Miescher Instiute for Biomedical Research, Fabrikstrasse 24, 4056 Basel, Switzerland
Learning-Based Robust Control: Unifying Exploration and Distributional Robustness for Reliable Robotics via Free Energy
Mar 6, 2026Hozefa Jesawada, Giovanni Russo, Abdalla Swikir +1Robust Control Distributionally Robust RL
Mechanical Engineering Program, New York University Abu Dhabi, Abu Dhabi, UAE. · Department of Information and Electrical Engineering & Applied Mathematics, University of Salerno, Fisciano, Italy. · Mohammed bin Zayed University for Artificial Intelligence, Abu Dhabi, UAE.
Probabilistic Dreaming for World Models
Mar 5, 2026Gavin WongWorld Model Learning World Models
Yale University, New Haven, CT
Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback
Mar 4, 2026Fabian Domberg, Georg SchildbachRobot Policy Adaptation Continual Robot Learning
Autonomous Systems Lab (ASL), Institute for Electrical Engineering in Medicine, University of Lübeck, 23562 Lübeck, Germany
Next Embedding Prediction Makes World Models Stronger
Mar 3, 2026George Bredis, Nikita Balagansky, Daniil Gavrilov +1Model-Based RL Partially Observable RL
T-Tech.
State-Action Inpainting Diffuser for Continuous Control with Delay
Mar 2, 2026Dongqi Han, Wei Wang, Enze Zhang +1Delayed RL Reinforcement Learning
Microsoft Research Asia · University of Pennsylvania · Shanghai Jiaotong University
Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
Mar 2, 2026Shaohuai Liu, Weirui Ye, Yilun Du +1Multi-Task RL Model-Based RL
Texas A&M University · MIT · Harvard University
Self-Curriculum Model-based Reinforcement Learning for Shape Control of Deformable Linear Objects
Feb 25, 2026Zhaowei Liang, Song Wang, Zhao Jin +2Deformable Object Manipulation Curriculum RL
All authors are with the Department of Mechanical Engineering, Tsinghua University, Beijing, China.
ALPACA: A Reinforcement Learning Environment for Medication Repurposing and Treatment Optimization in Alzheimer's Disease
Feb 22, 2026Nolan Brady, Tom YehAlzheimer's Disease Model-Based RL
University of Colorado Boulder, United States
Learning to unfold cloth: Scaling up world models to deformable object manipulation
Feb 18, 2026Jack Rome, Stephen James, Subramanian RamamoorthyDeformable Object Manipulation Generalization in Robotic Manipulation
University of Edinburgh · Imperial College London
World Models for Policy Refinement in StarCraft II
Feb 16, 2026Yixin Zhang, Ziyi Wang, Yiming Rong +6Game-Playing Agents Action-Conditioned World Models
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
Near-Optimal Sample Complexity for Online Constrained MDPs
Feb 16, 2026Chang Liu, Yunfan Li, Lin F. YangConstrained RL Safe RL
University of California, Los Angeles
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Feb 15, 2026Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11World Models for Robotics World Models
University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy +2
Coupled Local and Global World Models for Efficient First Order RL
Feb 5, 2026Joseph Amigo, Rooholla Khorrambakht, Nicolas Mansard +1Model-Based RL World Models for Robotics
Machines in Motion Laboratory, New York University, USA · LAAS-CNRS, Universit´e de Toulouse, CNRS, Toulouse, France · Artificial and Natural Intelligence Toulouse Institute, Toulouse, France
Meta-RL with Bayesian Linear Task Models
Dec 24, 2025Jingyang You, Hanna KurniawatiRepresentation Learning Reinforcement Learning
School of Computing Australian National University
Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes
Dec 17, 2025Hanqing Jin, Renyuan Xu, Yanzhao YangRL Control Reinforcement Learning
Mathematical Institute, University of Oxford · Department of Management Science and Engineering, Stanford University
Infinitesimal Operator World Models: Finite-Sample Guarantees for Offline Reinforcement Learning
Nov 13, 2025Nicolas Hoischen, Petar Bevanda, Max Beier +3Offline RL Model-Based RL
TU Munich · ShanghaiTech University
Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
Oct 16, 2025Shiqi Chen, Tongyao Zhu, Zian Wang +8RL Exploration Policy Learning
City University of Hong Kong · National University of Singapore · The Hong Kong Polytechnic University +5
Quantum Bayesian Networks Can Speed up Reinforcement Learning in Partially Observable Environments
Jul 24, 2025Gilberto Cunha, Alexandra Ramôa, André Sequeira +2Partially Observable RL Bayesian RL
High-Assurance Software Laboratory (HASLab), INESC TEC, Portugal · Department of Computer Science, University of Minho, Portugal · International Iberian Nanotechnology Laboratory (INL), Portugal
Fully Offline Reinforcement Learning
May 28, 2025Mattie Fellows, Clarisse Wibault, Uljad Berdica +3Bayesian RL Offline RL
Foerster Lab for AI Research (FLAIR), Department of Engineering Science, University of Oxford · Machine Learning Research Group, Department of Engineering Science, University of Oxford
Meta-reinforcement learning with minimum attention
May 22, 2025Shashank Gupta, Pilhwa LeeMeta-Reinforcement Learning Policy Learning
Department of EECS University of Michigan Ann Arbor, MI 48109 · Department of Mathematics Morgan State University Baltimore, MD 21251

Mar 18, 2026J/K move · Enter open · S save

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation

Naoki Morihira, Amal Nahar, Kartik Bharadwaj, Yasuhiro Kato+2

Honda R&D Co., Ltd. · The University of Tokyo · RIKEN AIP

Model-Based RL World Model Learning Representation Learning for RL Self-Supervised Visual Representation Learning

Open paper AskPDF arXiv

A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representations that distill essential information from irrelevant visual details. While promising, reconstruction-based methods often waste capacity on large task-irrelevant regions. Decoder-free methods instead learn robust representations by leveraging Data Augmentation (DA), but reliance on such external regularizers limits versatility. We propose R2-Dreamer, a decoder-free MBRL framework with a self-supervised objective that serves as an internal regularizer, preventing representation collapse without resorting to DA. The core of our method is a redundancy-reduction objective inspired by Barlow Twins, which can be easily integrated into existing frameworks. On DeepMind Control Suite and Meta-World, R2-Dreamer is competitive with strong baselines such as DreamerV3 and TD-MPC2 while training 1.59x faster than DreamerV3, and yields substantial gains on DMC-Subtle with tiny task-relevant objects. These results suggest that an effective internal regularizer can enable versatile, high-performance decoder-free MBRL. Code is available at https://github.com/NM512/r2dreamer.