Reinforcement Learning

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation AISTATS 2024 Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning ICLR 2024 Optimistic Information Directed Sampling COLT 2024 P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL AAAI 2024 PAE: Reinforcement Learning from External Knowledge for Efficient Exploration ICLR 2024 PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024 PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning NeurIPS 2024 Performative Reinforcement Learning in Gradually Shifting Environments UAI 2024 Periodic agent-state based Q-learning for POMDPs NeurIPS 2024 Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning NeurIPS 2024 Policy Improvement using Language Feedback Models NeurIPS 2024 Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning ICLR 2024 Power Mean Estimation in Stochastic Monte-Carlo Tree Search UAI 2024 Predicting Future Actions of Reinforcement Learning Agents NeurIPS 2024 PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference NeurIPS 2024 Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning ICLR 2024 Privileged Sensing Scaffolds Reinforcement Learning ICLR 2024 Prototypical Reward Network for Data-Efficient RLHF ACL 2024 Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback ICLR 2024 Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning ICLR 2024 Pure-Past Action Masking AAAI 2024 QGFN: Controllable Greediness with Action Values NeurIPS 2024 Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification ICLR 2024 Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces NeurIPS 2024 Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation NeurIPS 2024