Skip to content

shreyassr123/Multi-Step-Markov-Games

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 

Repository files navigation

A Multi-step Minimax Q-learning Algorithm

This repository contains the code for the new multi-step algorithm proposed for solving two-player zero-sum stochastic games. This repository can be utilized to reproduce the results provided in the paper titled "A Multi-step Minimax Q-learning algorithm for two-player zero-sum Markov games."

Requirements: nashpy package

Acknowledgments

This code is based on and adapted from Two-Player-SOR. Many thanks to the original authors for their contributions.

About

A multi-step two-player zero-sum games

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages