Model-Based RL

Open-World Reinforcement Learning over Long Short-Term Imagination ICLR 2025 Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning COLT 2025 Optimistic Q-learning for average reward and episodic reinforcement learning extended abstract COLT 2025 Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control ICLR 2025 Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization ICML 2025 Partially Observable Reinforcement Learning with Memory Traces ICML 2025 PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning ICML 2025 Policy Gradient with Tree Expansion ICML 2025 Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search ICML 2025 Provably Efficient Exploration in Inverse Constrained Reinforcement Learning ICML 2025 PWM: Policy Learning with Multi-Task World Models ICLR 2025 Q-function Decomposition with Intervention Semantics for Factored Action Spaces AISTATS 2025 Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes ICML 2025 R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning ICML 2025 Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens ICML 2025 Regret Bounds for Robust Online Decision Making COLT 2025 Regret-Free Reinforcement Learning for Temporal Logic Specifications ICML 2025 Reinforcement Learning with Segment Feedback ICML 2025 Relational Object-Centric Actor-Critic CLeaR 2025 Residual-MPPI: Online Policy Customization for Continuous Control ICLR 2025 Reward-free World Models for Online Imitation Learning ICML 2025 Risk-Sensitive Variational Actor-Critic: A Model-Based Approach ICLR 2025 Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation UAI 2025 Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction ICML 2025 Sample-Efficient Online Control Policy Learning with Real-Time Recursive Model Updates CoRL 2025