Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs

8 August 2024

Papers citing "Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs"

5 / 5 papers shown

Title
SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning Tianjian Li Daniel Khashabi 23 0 0 05 May 2025
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 34 11 0 03 Oct 2022
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs Dongruo Zhou Quanquan Gu 47 36 0 23 May 2022
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach Andrew Wagenmaker Yifang Chen Max Simchowitz S. Du Kevin G. Jamieson 58 31 0 07 Dec 2021