Methods

Maximum Entropy Softmax Policy Gradient via Entropy Advantage Estimation IJCAI 2025 Maximum Total Correlation Reinforcement Learning ICML 2025 MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization ICLR 2025 MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity COLING 2025 MDP Geometry, Normalization and Reward Balancing Solvers AISTATS 2025 Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents EMNLP 2025 Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents JMLR 2025 MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning ICML 2025 Meta-Black-Box-Optimization through Offline Q-function Learning ICML 2025 Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding ICML 2025 MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility ICLR 2025 MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning AAAI 2025 MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning EMNLP 2025 Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback ICML 2025 Minimax Optimal Reinforcement Learning with Quasi-Optimism ICLR 2025 Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning IJCNLP 2025 Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications L4DC 2025 Misspecified Q-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error ICLR 2025 Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization ICLR 2025 Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn ICML 2025 Model-Based Exploration in Monitored Markov Decision Processes ICML 2025 Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning ICLR 2025 Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds ICLR 2025 ModelDiff: Symbolic Dynamic Programming for Model-Aware Policy Transfer in Deep Q-Learning AAAI 2025 Model predictive control is almost optimal for restless bandits COLT 2025