Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs

18 May 2022

Papers citing "Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs"

6 / 6 papers shown

Title
Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward Washim Uddin Mondal Vaneet Aggarwal 14 2 0 04 May 2023
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs Zixuan Dong Che Wang Keith Ross 18 3 0 07 Sep 2022
Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback Tiancheng Jin Tal Lancewicki Haipeng Luo Yishay Mansour Aviv A. Rosenberg 59 21 0 31 Jan 2022
Learning Stationary Nash Equilibrium Policies in $n$ -Player Stochastic Games with Independent Chains S. Rasoul Etesami 8 6 0 28 Jan 2022
UCB Momentum Q-learning: Correcting the bias without forgetting Pierre Menard O. D. Domingues Xuedong Shang Michal Valko 72 40 0 01 Mar 2021
Bounded regret in stochastic multi-armed bandits Sébastien Bubeck Vianney Perchet Philippe Rigollet 56 90 0 06 Feb 2013