On Reinforcement Learning for Turn-based Zero-sum Markov Games

On Reinforcement Learning for Turn-based Zero-sum Markov Games

© 2020 Owner/Author. We consider the problem of finding Nash equilibrium for two-player turn-based zero-sum games. Inspired by the AlphaGo Zero (AGZ) algorithm, we develop a Reinforcement Learning based approach. Specifically, we propose Explore-Improve-Supervise (EIS) method that combines "exp...

Full description

Bibliographic Details
Main Authors: Shah, D, Somani, V, Xie, Q, Xu, Z
Other Authors: Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Format: Article
Language:English
Published: ACM 2021
Online Access:https://hdl.handle.net/1721.1/137142

Internet

https://hdl.handle.net/1721.1/137142

Similar Items