Saved in:
Bibliographic Details
Main Authors: R, Shreyas S, Vijesh, Antony
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.04240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915503697559552
author R, Shreyas S
Vijesh, Antony
author_facet R, Shreyas S
Vijesh, Antony
contents An interesting iterative procedure is proposed to solve a two-player zero-sum Markov games. Under suitable assumption, the boundedness of the proposed iterates is obtained theoretically. Using results from stochastic approximation, the almost sure convergence of the proposed two-step minimax Q-learning is obtained theoretically. More specifically, the proposed algorithm converges to the game theoretic optimal value with probability one, when the model information is not known. Numerical simulation authenticate that the proposed algorithm is effective and easy to implement.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Multi-Step Minimax Q-learning Algorithm for Two-Player Zero-Sum Markov Games
R, Shreyas S
Vijesh, Antony
Machine Learning
An interesting iterative procedure is proposed to solve a two-player zero-sum Markov games. Under suitable assumption, the boundedness of the proposed iterates is obtained theoretically. Using results from stochastic approximation, the almost sure convergence of the proposed two-step minimax Q-learning is obtained theoretically. More specifically, the proposed algorithm converges to the game theoretic optimal value with probability one, when the model information is not known. Numerical simulation authenticate that the proposed algorithm is effective and easy to implement.
title A Multi-Step Minimax Q-learning Algorithm for Two-Player Zero-Sum Markov Games
topic Machine Learning
url https://arxiv.org/abs/2407.04240