Multiple policy value Monte Carlo tree search

Li Cheng Lan, Wei Li, Ting Han Wei, I. Chen Wu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Many of the strongest game playing programs use a combination of Monte Carlo tree search (MCTS) and deep neural networks (DNN), where the DNNs are used as policy or value evaluators. Given a limited budget, such as online playing or during the self-play phase of AlphaZero (AZ) training, a balance needs to be reached between accurate state estimation and more MCTS simulations, both of which are critical for a strong game playing agent. Typically, larger DNNs are better at generalization and accurate evaluation, while smaller DNNs are less costly, and therefore can lead to more MCTS simulations and bigger search trees with the same budget. This paper introduces a new method called the multiple policy value MCTS (MPV-MCTS), which combines multiple policy value neural networks (PV-NNs) of various sizes to retain advantages of each network, where two PV-NNs fS and fL are used in this paper. We show through experiments on the game NoGo that a combined fS and fL MPV-MCTS outperforms single PV-NN with policy value MCTS, called PV-MCTS. Additionally, MPV-MCTS also outperforms PV-MCTS for AZ training.

Original languageEnglish
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4704-4710
Number of pages7
ISBN (Electronic)9780999241141
DOIs
StatePublished - 1 Jan 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: 10 Aug 201916 Aug 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
CountryChina
CityMacao
Period10/08/1916/08/19

Fingerprint Dive into the research topics of 'Multiple policy value Monte Carlo tree search'. Together they form a unique fingerprint.

Cite this