Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Qinbo, Mondal, Washim Uddin, Aggarwal, Vaneet
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911769864175616
author Bai, Qinbo
Mondal, Washim Uddin
Aggarwal, Vaneet
author_facet Bai, Qinbo
Mondal, Washim Uddin
Aggarwal, Vaneet
contents In this paper, we consider an infinite horizon average reward Markov Decision Process (MDP). Distinguishing itself from existing works within this context, our approach harnesses the power of the general policy gradient-based algorithm, liberating it from the constraints of assuming a linear MDP structure. We propose a policy gradient-based algorithm and show its global convergence property. We then prove that the proposed algorithm has $\tilde{\mathcal{O}}({T}^{3/4})$ regret. Remarkably, this paper marks a pioneering effort by presenting the first exploration into regret-bound computation for the general parameterized policy gradient algorithm in the context of average reward scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2309_01922
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
Bai, Qinbo
Mondal, Washim Uddin
Aggarwal, Vaneet
Machine Learning
Artificial Intelligence
In this paper, we consider an infinite horizon average reward Markov Decision Process (MDP). Distinguishing itself from existing works within this context, our approach harnesses the power of the general policy gradient-based algorithm, liberating it from the constraints of assuming a linear MDP structure. We propose a policy gradient-based algorithm and show its global convergence property. We then prove that the proposed algorithm has $\tilde{\mathcal{O}}({T}^{3/4})$ regret. Remarkably, this paper marks a pioneering effort by presenting the first exploration into regret-bound computation for the general parameterized policy gradient algorithm in the context of average reward scenarios.
title Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2309.01922