Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal

10 June 2019

Papers citing "Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal"

10 / 60 papers shown

Title
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon Zihan Zhang Xiangyang Ji S. Du OffRL 34 104 0 28 Sep 2020
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity Kaipeng Zhang Sham Kakade Tamer Bacsar Lin F. Yang 52 120 0 15 Jul 2020
A Provably Efficient Sample Collection Strategy for Reinforcement Learning Jean Tarbouriech Matteo Pirotta Michal Valko A. Lazaric OffRL 25 16 0 13 Jul 2020
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning Ming Yin Yu Bai Yu Wang OffRL 44 31 0 07 Jul 2020
$Q$ -learning with Logarithmic Regret Kunhe Yang Lin F. Yang S. Du 43 59 0 16 Jun 2020
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model Gen Li Yuting Wei Yuejie Chi Yuxin Chen 39 125 0 26 May 2020
Learning Near Optimal Policies with Low Inherent Bellman Error Andrea Zanette A. Lazaric Mykel Kochenderfer Emma Brunskill OffRL 24 221 0 29 Feb 2020
Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium Qiaomin Xie Yudong Chen Zhaoran Wang Zhuoran Yang 41 124 0 17 Feb 2020
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning Ming Yin Yu Wang OffRL 29 80 0 29 Jan 2020
Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity Aaron Sidford Mengdi Wang Lin F. Yang Yinyu Ye 13 70 0 29 Aug 2019