Model-Based RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 243% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 142

All topics

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
Jun 17, 2026Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang +1Pairwise Preference Evaluation RL Exploration
Learning, Embodied Autonomy, and Forecasting (LEAF) Lab, University of Toronto
Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards
Jun 17, 2026Zirong LiReward Modeling Reinforcement Learning
Tiangong University
Stealthy World Model Manipulation via Data Poisoning
Jun 17, 2026Yibin Hu, Xiaolin Sun, Zizhan ZhengWorld Model Learning Adversarial Attacks
Department of Computer Science Tulane University New Orleans, LA, USA
SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping
Jun 17, 2026Xiaowen Hu, Linqi Ye, Yudi Zhu +4Robot Locomotion RL for Legged Locomotion
Institute of Artificial Intelligence, Shanghai University, Shangda Road 99, Baoshan District, 200444, Shanghai, China · Institute of Machine Intelligence, University of Shanghai for Science and Technology, Jungong Road 516, Yangpu District, 200093, Shanghai, China
WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
Jun 16, 2026Zezhong Qian, Xiaowei Chi, Yu Qi +3World Model Learning Action-Conditioned World Models
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Northeastern University · Tsinghua University
BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models
Jun 15, 2026Shaowei Zhang, Jiahan Cao, Xunlan Zhou +2World Models Latent World Models
1National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · School of Intelligence Science and Technology, Nanjing University, China
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
Jun 15, 2026Kai Tang, Peidong Jia, Zhong Chu +15Constrained RL Robot Safety
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · Nanyang Technological University +2
Causal Object-Centric Models for Planning with Monte Carlo Tree Search
Jun 12, 2026Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik +1World Models World Model-Based Planning
MIRAI Moscow, Russia · CogAILab & MIRAI Moscow, Russia
PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation
Jun 9, 2026Abhinav Kumar, Soshi Iba, Rana Soltani Zarrin +1Online System Identification Dexterous Manipulation
University of Michigan · Honda Research Institute USA
MODIP: Efficient Model-Based Optimization for Diffusion Policies
Jun 9, 2026Zakariae El Asri, Philippe Gratias-Quiquandon, Nicolas Thome +1Robot Policy Learning Robot Policy Adaptation
Sorbonne Université, CNRS, ISIR, F-75005 Paris, France · Institut Universitaire de France (IUF)
MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
Jun 9, 2026Codrin Crismariu, Ryan K. CosnerHumanoid Robot Locomotion Terrain-Aware Robot Locomotion
Department of Mechanical Engineering Tufts University, Medford, MA, United States
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Jun 5, 2026Hikaru Shindo, Yu Deng, Teng Cao +5Reinforcement Learning World Models
1Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Germany · Department of Computer Science, Technical University of Darmstadt, Germany · 2Hessian Center for Artificial Intelligence (hessian.AI), Germany +3
Post-Hoc Robustness for Model-Based Reinforcement Learning
Jun 2, 2026Siemen Herremans, Ali Anwar, Siegfried MercelisAdversarial Robustness Robust RL
1IDLab - University of Antwerp, imec
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Jun 1, 2026Raman AroraRegret Minimization in RL Imperfect-Information Games
Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
May 31, 2026Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele +2Robotic RL Safe RL
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, 52062 Aachen, Germany
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
May 30, 2026Fuyuan Qian, Menglong Zhang, Song Wang +1Representation Learning Offline RL
Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China · AI Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China · Omni-Intelligence, Shenzhen, Guangdong, China +1
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
May 30, 2026Hongqiang Lin, Pengfei Wang, Nenggan ZhengReinforcement Learning Bayesian RL
Zhejiang University, Hangzhou, China.
Cortex and subcortex play distinct roles over learning when cortical memory is limited
May 30, 2026Matthew Farrell, Taro ToyoizumiComputational Cognitive Modeling Reinforcement Learning
Laboratory for Neural Computation and Adaptation RIKEN Center for Brain Science, Wako, Japan · Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan.
StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
May 29, 2026Junwon Seo, Sushant Veer, Ran Tian +6Video Diffusion Models Action-Conditioned World Models
Carnegie Mellon University · NVIDIA Research · University of Washington +1
Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
May 29, 2026Ha Manh Bui, Metod Jazbec, Eric Nalisnick +1Reinforcement Learning Diffusion Policy
Department of Computer Science, Johns Hopkins University, Baltimore, MD, U.S.A. · AMLab, University of Amsterdam, Amsterdam, Netherlands
Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
May 27, 2026Christoph Dann, Yishay Mansour, Mehryar MohriSim-to-Real Transfer Active Learning
Google Research · Tel Aviv University and Google Research · Google Research and Courant Institute of Mathematical Sciences
Accelerating Reinforcement Learning Training Using Simulation Surrogate Models
May 26, 2026Mohammadmahdi Ghasemloo, David J. Eckman, Yaxian LiSurrogate Modeling Reinforcement Learning
Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA · Intuit AI, Mountain View, CA, USA
Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization
May 25, 2026Xiaoyuan Cheng, Wenxuan Yuan, Zhancun Mu +5World Model Learning Diffusion Policy
Dynamic Systems Lab, University College London · College of Computing and Data Science, Nanyang Technological University · School of Intelligence Science and Technology, Peking University +3
Generative OOD-regularized Model-based Policy Optimization
May 23, 2026Aysin Tumay, Jiahe Huang, Elise Jortberg +1Offline RL OOD Detection
University of California, San Diego · Abiomed
Neuro-Inspired Inverse Learning for Planning and Control
May 22, 2026Maryna Kapitonova, Tonio BallRobot Policy Learning Model-Based Planning
NeuroMentum AI · IMBIT, University of Freiburg, Germany
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
May 21, 2026Romil V. Sonigra, P. R. KumarLatent Dynamics Modeling Jacobian Regularization
Texas A&M University · Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843
Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
May 19, 2026Yang Fu, Haomin Bao, Rohit Sonker +4RL Benchmarks Offline RL
Central South University · Chongqing University · Carnegie Mellon University +1
Sampling-Based Safe Reinforcement Learning
May 19, 2026Luca Vignola, Bruce D. Lee, Manish Prajapat +4Robot Safety Safe RL
ETH Zurich
PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics
May 18, 2026Xueyu Luan, Chenwei ShiDynamical Systems Reinforcement Learning
School of Electronic and Information Engineering Tongji University Shanghai 200092, China · Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai 200092, China
Transfer Learning for Customized Car Racing Environments
May 18, 2026Benedict Florance Arockiaraj, Richard Chang, Wesley YeeAutonomous Racing Cross-Domain Transfer Learning
SEAS

Jun 17, 2026, cs.LGJ/K move · Enter open · S save

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning

Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang, Nicholas Rhinehart

Learning, Embodied Autonomy, and Forecasting (LEAF) Lab, University of Toronto

Pairwise Preference Evaluation RL Exploration Model-Based Planning Sample-Efficient RL Model-Based RL Preference-Based RL

Open paper AskPDF arXiv

Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.

Momentum

Related topics

Latest papers 142