A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs

24 June 2021

Papers citing "A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs"

4 / 4 papers shown

Title
Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition Zhong Zheng Haochen Zhang Lingzhou Xue OffRL 78 2 0 10 Oct 2024
Settling the Sample Complexity of Online Reinforcement Learning Zihan Zhang Yuxin Chen Jason D. Lee S. Du OffRL 98 21 0 25 Jul 2023
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning Andrea Zanette Martin J. Wainwright OOD 38 5 0 01 Jun 2022
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints Chi Jin Zhuoran Yang Zhaoran Wang OffRL 122 166 0 06 Jan 2021