Offline RL

Rates for Offline Reinforcement Learning with Adaptively Collected Data L4DC 2025 Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens ICML 2025 ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning ICML 2025 Relational Neurosymbolic Markov Models AAAI 2025 Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning ICML 2025 Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs ICML 2025 ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations CoRL 2025 Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning ICLR 2025 Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization ICML 2025 Robust Reward Alignment via Hypothesis Space Batch Cutting ICML 2025 Safe Decision Transformer with Learning-based Constraints L4DC 2025 Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics ICML 2025 Sample-Optimal Agnostic Boosting with Unlabeled Data ICML 2025 Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning ICLR 2025 Selective Uncertainty Propagation in Offline RL AAAI 2025 SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation ICLR 2025 Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues AAAI 2025 SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch AAAI 2025 SPO: Self Preference Optimization with Self Regularization EMNLP 2025 Stabilizing and Accelerating Autofocus with Expert Trajectory Regularized Deep Reinforcement Learning CVPR 2025 Stable Offline Value Function Learning with Bisimulation-based Representations ICML 2025 State Revisit and Re-explore: Bridging Sim-to-Real Gaps in Offline-and-Online Reinforcement Learning with An Imperfect Simulator IJCAI 2025 Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs ICLR 2025 SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning AAAI 2025 Supervised Optimism Correction: Be Confident When LLMs Are Sure ACL 2025