Reinforcement Learning

Dynamic Uncertainty Estimation for Offline Reinforcement Learning AAAI 2025 DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making ICML 2025 DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI CVPR 2025 DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation ICCV 2025 EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization ICML 2025 EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow ICCV 2025 Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs ICLR 2025 Efficient Active Imitation Learning with Random Network Distillation ICLR 2025 Efficient and Robust Reinforcement Learning from Human Feedback AAAI 2025 Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation AAAI 2025 Efficient Cross-Episode Meta-RL ICLR 2025 Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning ICLR 2025 Efficient Diversity-based Experience Replay for Deep Reinforcement Learning IJCAI 2025 Efficient Dynamic Ensembling for Multiple LLM Experts IJCAI 2025 Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection CoRL 2025 Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning AISTATS 2025 Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction ICLR 2025 Efficient Imitation under Misspecification ICLR 2025 Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning EMNLP 2025 Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution AAAI 2025 Efficiently Escaping Saddle Points for Policy Optimization UAI 2025 Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling ICLR 2025 Efficient Multi-Policy Evaluation for Reinforcement Learning AAAI 2025 Efficient Off-Policy Learning for High-Dimensional Action Spaces ICLR 2025 Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data ICLR 2025