Reinforcement Learning

Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints ICML 2025 Policy-Regret Minimization in Markov Games with Function Approximation ICML 2025 Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning ICML 2025 PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization ICLR 2025 Position: Constants are Critical in Regret Bounds for Reinforcement Learning ICML 2025 Position: Lifetime tuning is incompatible with continual reinforcement learning ICML 2025 POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition ICLR 2025 Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search ICML 2025 Practicable Black-Box Evasion Attacks on Link Prediction in Dynamic Graphs—a Graph Sequential Embedding Method AAAI 2025 Prediction-Aware Learning in Multi-Agent Systems ICML 2025 Predictive Red Teaming: Breaking Policies Without Breaking Robots CoRL 2025 PRED: Performance-oriented Random Early Detection for Consistently Stable Performance in Datacenters NSDI 2025 Preference Adaptive and Sequential Text-to-Image Generation ICML 2025 Preference-based Deep Reinforcement Learning for Historical Route Estimation IJCAI 2025 Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies ICML 2025 Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization ICML 2025 Preference Elicitation for Offline Reinforcement Learning ICLR 2025 Preference Optimization for Combinatorial Optimization Problems ICML 2025 Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline ICLR 2025 Primal-Dual Spectral Representation for Off-policy Evaluation AISTATS 2025 Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents ICML 2025 Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF JMLR 2025 Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models CVPR 2025 PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction CoRL 2025 Private Federated Learning using Preference-Optimized Synthetic Data ICML 2025