Model-Based RL

Active Intelligence in Video Avatars via Closed-loop World Modeling CVPR 2026 Adapting World Models with Latent-State Dynamics Residuals L4DC 2026 AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning CVPR 2026 Analytic Planning under Uncertainty with Moment Closure UAI 2026 DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration CVPR 2026 GeoWorld: Geometric World Models CVPR 2026 IPR-1: Interactive Physical Reasoner CVPR 2026 Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making L4DC 2026 Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs (extended abstract) COLT 2026 Model-Based Reinforcement Learning under Random Observation Delays L4DC 2026 Motus: A Unified Latent Action World Model CVPR 2026 Offline Reinforcement Learning for Rotation Profile Control in Tokamaks L4DC 2026 Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model CVPR 2026 RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model CVPR 2026 TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint L4DC 2026 WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning L4DC 2026 Accurate and Efficient World Modeling with Masked Latent Transformers ICML 2025 Achieving Õ(√T) Regret in Average-Reward POMDPs with Known Observation Models AISTATS 2025 Action-Conditioned Hamiltonian Generative Networks (AC-HGN) for Supervised and Reinforcement Learning L4DC 2025 ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning ICLR 2025 AdaWM: Adaptive World Model based Planning for Autonomous Driving ICLR 2025 An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints ICML 2025 Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning ICLR 2025 A Pontryagin Perspective on Reinforcement Learning L4DC 2025 ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly CoRL 2025