Model-Based RL

RL: Reinforcement Learning

Ask about this topic

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

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

  1. A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown Lévy Process Dynamics

    Apr 2, 2025Qihao Ye, Xiaochuan Tian, Yuhua ZhuReinforcement LearningValue Function Estimation

  2. Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective

    Feb 17, 2025Yu-Wei Yang, Wei Hung, Yun-Ming Chan +2Model SelectionOffline RL

    Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Applied Machine Learning, Meta AI, Menlo Park, CA, USA

  3. Safe Learning Control with Optimality and Stability Guarantees

    Jan 26, 2025Xinyang Wang, Hongwei Zhang, Shimin Wang +2Control Barrier FunctionsRobust Control

    Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Guangdong 518055, China · School of Data Science, Lingnan University, Hong Kong · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, with M3S, SMART, and with MIT CSAIL +1

  4. ProSpec RL: Plan Ahead, then Execute

    Jul 31, 2024Liangliang Liu, Yi Guan, BoRan Wang +5Reinforcement LearningRisk-Sensitive RL

    1The Faculty of Computing, Harbin Institute of Technology, Harbin, China · 2The Artificial Intelligence Institute, Harbin Institute of Technology, ShenZhen, China · 3The Artificial Intelligence Institute, Harbin Institute of Technology, Harbin, China

  5. Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation

    Apr 2, 2024Carlos Plou, Ana C. Murillo, Ruben Martinez-CantinModel-Based RLData-Efficient Robot Learning

    All authors are with the Instituto de Investigación en Ingeniería de Aragón (i3A) and DIIS, University of Zaragoza