Offline RL

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values EMNLP 2025 Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework AAAI 2025 Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training RSS 2025 Dynamic Uncertainty Estimation for Offline Reinforcement Learning AAAI 2025 Efficient Multi-Policy Evaluation for Reinforcement Learning AAAI 2025 Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data ICLR 2025 Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model ICML 2025 Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data AAAI 2025 Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning AAAI 2025 Evaluation of Active Feature Acquisition Methods for Time-varying Feature Settings JMLR 2025 Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank ICLR 2025 Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies ICLR 2025 Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset ICLR 2025 Flow Q-Learning ICML 2025 FOSP: Fine-tuning Offline Safe Policy through World Models ICLR 2025 From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting CoRL 2025 Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning ICML 2025 GOODLIAR: A Reinforcement Learning-Based Deceptive Agent for Disrupting LLM Beliefs on Foundational Principles ACL 2025 Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning ICML 2025 Graph Diffusion for Robust Multi-Agent Coordination ICML 2025 Habitizing Diffusion Planning for Efficient and Effective Decision Making ICML 2025 HALO : Human Preference Aligned Offline Reward Learning for Robot Navigation CoRL 2025 Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data AISTATS 2025 Imagination-Limited Q-Learning for Offline Reinforcement Learning IJCAI 2025