Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

17 May 2023

Papers citing "Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning"

6 / 6 papers shown

Title
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning Mitsuhiko Nakamoto Yuexiang Zhai Anika Singh Max Sobol Mark Yi-An Ma Chelsea Finn Aviral Kumar Sergey Levine OffRL OnRL 96 68 0 09 Mar 2023
Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation Dan Qiao Yu-Xiang Wang OffRL 38 11 0 03 Oct 2022
A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning Zixiang Chen C. J. Li An Yuan Quanquan Gu Michael I. Jordan OffRL 90 25 0 30 Sep 2022
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL Ruiquan Huang J. Yang Yingbin Liang OffRL 35 8 0 28 Jun 2022
UCB Momentum Q-learning: Correcting the bias without forgetting Pierre Menard O. D. Domingues Xuedong Shang Michal Valko 50 35 0 01 Mar 2021
Reward-Free Exploration for Reinforcement Learning Chi Jin A. Krishnamurthy Max Simchowitz Tiancheng Yu OffRL 82 181 0 07 Feb 2020