Deep RL

DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models ICML 2025 DIME: Diffusion-Based Maximum Entropy Reinforcement Learning ICML 2025 Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback ACL 2025 DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data EMNLP 2025 Discovering Options That Minimize Average Planning Time AAAI 2025 DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model ICCV 2025 Distributional Reinforcement Learning with Dual Expectile-Quantile Regression UAI 2025 Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework AAAI 2025 Diversity-Aware Reinforcement Learning for de novo Drug Design IJCAI 2025 Diving into Self-Evolving Training for Multimodal Reasoning ICML 2025 Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective ICML 2025 DPO Meets PPO: Reinforced Token Optimization for RLHF ICML 2025 DSBRouter: End-to-end Global Routing via Diffusion Schrödinger Bridge ICML 2025 DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback AAAI 2025 DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation AAAI 2025 Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training RSS 2025 DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making ICML 2025 EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization ICML 2025 Efficient Active Imitation Learning with Random Network Distillation ICLR 2025 Efficient and Robust Reinforcement Learning from Human Feedback AAAI 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 Exploration and Discriminative World Model Learning with an Object-Centric Abstraction 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