Deep Reinforcement Learning for 5*5 Multiplayer Go
Artificial Intelligence
2024-05-24 v1
Abstract
In recent years, much progress has been made in computer Go and most of the results have been obtained thanks to search algorithms (Monte Carlo Tree Search) and Deep Reinforcement Learning (DRL). In this paper, we propose to use and analyze the latest algorithms that use search and DRL (AlphaZero and Descent algorithms) to automatically learn to play an extended version of the game of Go with more than two players. We show that using search and DRL we were able to improve the level of play, even though there are more than two players.
Keywords
Cite
@article{arxiv.2405.14265,
title = {Deep Reinforcement Learning for 5*5 Multiplayer Go},
author = {Brahim Driss and Jérôme Arjonilla and Hui Wang and Abdallah Saffidine and Tristan Cazenave},
journal= {arXiv preprint arXiv:2405.14265},
year = {2024}
}
Comments
Accepted in EvoApps at Evostar2023