Can I read Refined Analysis of FPL for Adversarial Markov Decision Processes on EtoBox?

Refined Analysis of FPL for Adversarial Markov Decision Processes by Wang, Yuanhao; Dong, Kefan is a scholarly article available to read on EtoBox.

What is Refined Analysis of FPL for Adversarial Markov Decision Processes about?

We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unknown. In both settings, Follow-the-PerturbedLeader (FPL) based algorithms have been proposed in previous literature. However, the established regret bounds for FPL based algorithms are worse than algorithms based on mirrordescent. We improve the analysis of FPL based algorithms in both settings, matching the current best regret bounds using faster and simpler algorithms.

Author

Wang, Yuanhao; Dong, Kefan

Published

2020

Language

EN