Methods

Optimizing Return Distributions with Distributional Dynamic Programming JMLR 2025 Optimizing RLHF Training for Large Language Models with Stage Fusion NSDI 2025 Optimizing Test-Time Compute via Meta Reinforcement Finetuning ICML 2025 Optimizing the Battery-Swapping Problem in Urban E-Bike Systems with Reinforcement Learning IJCAI 2025 OptionZero: Planning with Learned Options ICLR 2025 Order-Optimal Global Convergence for Actor-Critic with General Policy and Neural Critic Parametrization UAI 2025 Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs AISTATS 2025 ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization ICLR 2025 OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis ACL 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 OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination ICLR 2025 PAC Learning with Improvements ICML 2025 Pareto Set Learning for Multi-Objective Reinforcement Learning AAAI 2025 Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting AAAI 2025 Partially Observable Reference Policy Programming IJCAI 2025 Partially Observable Reinforcement Learning with Memory Traces ICML 2025 PASD: A Pixel-Adaptive Swarm Dynamics Approach for Unsupervised Low-Light Image Enhancement ICCV 2025 Patient-Specific Deep Reinforcement Learning for Automatic Replanning in Head-and-Neck Cancer Proton Therapy MLHC 2025 PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning ICLR 2025 Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data ICML 2025 Performative Reinforcement Learning with Linear Markov Decision Process AISTATS 2025 Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-Learning AAAI 2025 Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning ICML 2025 PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization ACL 2025