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

RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation
Oct 6, 2026Jing Xie, Shouwei Ruan, Yubin Wang +4Robot Policy Learning World Model Learning
MoE Key Lab of Artificial Intelligence, Institute of AI, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Beihang University, Beijing, China · The Hong Kong University of Science and Technology, Hong Kong, China +3
Considering Context: When World Models Need Context Encoders
Oct 5, 2026Oleg Smirnov, Sofiane Ennadir, John Pertoft +2Reinforcement Learning World Model Learning
King AI Labs, Microsoft Gaming
Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
Oct 5, 2026Shengtao Wen, Xiang Chen, Yu Tian +3World Model-Based Planning Action-Conditioned World Models
Nanjing University of Aeronautics and Astronautics, Nanjing, China · Tsinghua University, Beijing, China · Nanjing University, Nanjing, China
Optimal Control with Learned Critics under Unmodeled State Dependencies
Oct 4, 2026Philipp Schoch, Markus RyllResidual Dynamics Learning Robot Dynamics Learning
Autonomous Aerial Systems Lab Technical University of Munich
$R^2$ -WAM: Repair-and-Reject Post-Training for World Action Models
Oct 4, 2026Ruiyan Xu, Haisheng Su, Sixu Lin +4World Action Models Action-Conditioned World Models
The Chinese University of Hong Kong, Shenzhen · Manifold AI · Southeast University +1
Calibration-risk routing for controlled world-model adaptation
Oct 1, 2026Yifan Zhang, Liang ZhengWorld Models for Robotics World Models
Central South University
In CEM, a World Model Is Also a Proposal Mechanism
Oct 1, 2026Oliver Obst, Frieder StolzenburgBlack-Box Optimization Model-Based Planning
UNSW Sydney · Harz University of Applied Sciences
DashVMC: Real-Time Discrete World Model Control in Geometry Dash
Sep 30, 2026Florent Tariolle, Florian YgerAction-Conditioned World Models Model-Based RL
INSA Rouen Normandy
Beyond Policy Alignment: Closing the Planning-Learning Loop for Robot Control with Learned World Models
Sep 30, 2026Kowndinya Boyalakuntla, Yuhan Liu, Abdeslam BoulariasRobotic Control World Models for Robotics
Rutgers University
Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust
Sep 29, 2026Ziqi Wen, Ting Xu, Lianyu Wang +5Uncertainty Quantification World Model-Based Planning
Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 119228, Singapore · Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 119228, Singapore · Bioengineering Program, Biomedical Sciences Division (BioMed), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia +3
Model-Informed Safe Reinforcement Learning for Bipedal Locomotion via Step-to-Step Prediction
Sep 28, 2026Victor Paredes, Ayonga HereidHumanoid Robot Locomotion Control Barrier Functions
Mechanical and Aerospace Engineering, The Ohio State University, Columbus, OH, USA.
MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning
Sep 27, 2026Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de WittGame-Playing Agents World Model Learning
Department of Engineering Science, University of Oxford
Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
Sep 26, 2026Yi Xian Goh, Sze Jue Yang, Hao LuanData-Driven Control Model Predictive Control
Independent Researcher · Faculty of Computer Science and Information Technology, Universiti Malaya · School of Computing, National University of Singapore
Not All Errors Matter: Decision-Relevant Prediction Error Predicts Planning Quality
Sep 26, 2026Linhao Wang, Yiyan Fan, Dongjin HuangWorld Model-Based Planning Model-Based Planning
Shanghai Film Academy, Shanghai University
Spiking Neural Network Predicting Sequence of the External Worlds States in Model-Based Reinforcement Learning
Sep 23, 2026Mikhail KiselevWorld Models Spiking Neural Networks
Chuvash State University, Cheboxary, Russia
Dual-Frontier: When Can an Agent Trust Its World Model?
Sep 22, 2026Huatai Zhu, Qiang Chen, Ziqian Kou +5World Model-Based Planning Model-Based Planning
Central South University · The Hong Kong University of Science and Technology · Xiangjiang Laboratory +2
Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
Sep 21, 2026Kejia Hu, Wentong Zhai, Bo Zhao +1Robotic Manipulation Vision-Language-Action Models
Department of Electric Engineering, Korea Advanced Institute of Science and Technology · University Of Science and Technology Beijing · Shanghai Jiao Tong University +1
Efficient Bayes-Adaptive Reinforcement Learning with Temporal Logic Specifications
Sep 17, 2026Jonathan Hau, Alessandro AbateBayesian RL Safe RL
Department of Computer Science, University of Oxford, United Kingdom
A Convergence Framework for Deep $V$ -Learning: Error Propagation and Sharp Action-Gap Bounds
Sep 16, 2026Yury KolomeytsevReinforcement Learning Policy Learning
Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University
Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning
Sep 16, 2026Everest Yang, Skye Thompson, George D. KonidarisNon-Stationary RL Continual Robot Learning
Brown University, Providence, RI, USA
ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation
Sep 15, 2026Yushan Bai, Boyu Zheng, Zhiyang Mao +4Robot Policy Learning Contact-Rich Robotic Manipulation
CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · School of Intelligent Science and Technology, Xinjiang University +1
Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models
Sep 12, 2026Andreas Schwung, Steve Yuwono, Sofiene Lassoued +1Manufacturing RL Control
South Westphalia University of Applied Sciences, Soest 59494, Germany · Hochschule Düsseldorf University of Applied Sciences, Düsseldorf 40476, Germany
Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation
Sep 11, 2026Anqi Peter Li, Kaden KimCounterfactual Evaluation World Model Learning
Substrate Labs · UC Berkeley
Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning
Sep 10, 2026Fernando Palafox, David Fridovich-KeilTest-Time Adaptation World Model Learning
University of Texas at Austin Austin, TX, USA
Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
Sep 10, 2026Corentin Pla, Hugo Richard, Marc Abeille +1Reinforcement Learning Approximation Algorithms
CREST, ENSAE · Criteo AI Lab FairPlay Joint Team
HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy
Sep 9, 2026Zengjue Chen, Peidong Liu, Jiawei Li +1Robot Policy Learning World Models
Joy Future Academy, JD · School of Artificial Intelligence, Jilin University
CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning
Sep 8, 2026Pietro Noah Crestaz, Mohamed Yassine Kabouri, Nicolas Mansard +1RL for Robotics Reinforcement Learning
1Industrial Engineering Department, University of Trento, Trento, Italy. · 2LAAS-CNRS, Universit´e de Toulouse, CNRS, Toulouse, France. · 4Artificial and Natural Intelligence Toulouse Institute (ANITI), Toulouse. +1
World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain
Sep 2, 2026Yuxi Liu, Lijun Han, Ziming Wang +3Humanoid Robot Locomotion Terrain-Aware Robot Locomotion
1D-Robotics · 2Beijing University of Posts and Telecommunications · 3Harbin Institute of Technology +1
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Sep 1, 2026Tomáš Holeček, Viliam LisýImperfect-Information Games Zero-Sum Games
Artificial Intelligence Center, Department of Computer Science Faculty of Electrical Engineering, Czech Technical University in Prague
Reinforced Planning with Latent World Models
Aug 19, 2026Armin Sommer, Jannik SchillingWorld Model-Based Planning Robotic RL
Pantheon Industries

Oct 6, 2026, cs.ROJ/K move · Enter open · S save

RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation

Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang+3

MoE Key Lab of Artificial Intelligence, Institute of AI, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Beihang University, Beijing, China · The Hong Kong University of Science and Technology, Hong Kong, China+3

Robot Policy Learning World Model Learning Robot Navigation Action-Conditioned World Models Recursive Self-Improvement Model-Based RL

Open paper AskPDF arXiv

Long-horizon urban navigation requires sequential local decisions whose errors can compound over time. Imitation learning (IL) rarely learns from failures, while physical trial-and-error reinforcement learning (RL) is costly. Action-conditioned world models can provide imagined feedback by predicting visual consequences for candidate actions. However, a frozen world model may become less reliable as the policy evolves. In this paper, we introduce RIWANAV, a post-training framework that casts the coupled adaptation of a world model and an action model (policy) as task-specific recursive self-improvement (RSI). Each cycle alternates two updates. The world model evaluates policy actions through imagined outcomes, providing comparative feedback for group-relative policy optimization (GRPO). The improved policy then constructs a grounded self-curriculum, selecting expert-consistent action-video pairs by behavioral novelty and prediction error. The refined world model supplies feedback for the next policy update, closing the recursive self-improvement loop. Experiments show that RIWANAV outperforms training baselines and prior methods, validating the proposed recursive self-improvement loop between the policy and world model. Real-world trials further demonstrate its practical applicability.

Momentum

Related topics

Latest papers 142