Multi-agent Monte Carlo go

Soriano Marcolino, Leandro and Matsubara, Hitoshi (2011) Multi-agent Monte Carlo go. In: AAMAS '11 The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1 :. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, pp. 21-28. ISBN 9780982657157

Full text not available from this repository.

Abstract

In this paper we propose a Multi-Agent version of UCT Monte Carlo Go. We use the emergent behavior of a great number of simple agents to increase the quality of the Monte Carlo simulations, increasing the strength of the artificial player as a whole. Instead of one agent playing against itself, different agents play in the simulation phase of the algorithm, leading to a better exploration of the search space. We could significantly overcome Fuego, a top Computer Go software. Emergent behavior seems to be the next step of Computer Go development.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
81369
Deposited By:
Deposited On:
30 Aug 2016 11:02
Refereed?:
Yes
Published?:
Published
Last Modified:
16 Jul 2024 03:53