EvoMCTS: A scalable approach for general game learning

Amit Benbassat, Moshe Sipper

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

In this paper, we present the application of genetic programming as a generic game learning approach to zero-sum, deterministic, full-knowledge board games by evolving board-state evaluation functions to be used in conjunction with Monte Carlo tree search (MCTS). Our method involves evolving board-evaluation functions that are then used to guide the MCTS playout strategy. We examine several variants of Reversi, Dodgem, and Hex using strongly typed genetic programming, explicitly defined introns, and a selective directional crossover method. Our results show a proficiency that surpasses that of baseline handcrafted players using equal and in some cases greater amounts of search, with little domain knowledge and no expert domain knowledge. Moreover, our results exhibit scalability.

Original languageEnglish
Article number6744581
Pages (from-to)382-394
Number of pages13
JournalIEEE Transactions on Computational Intelligence and AI in Games
Volume6
Issue number4
DOIs
StatePublished - 1 Jan 2014

Keywords

  • Board games
  • Genetic programming
  • Monte Carlo methods, search

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'EvoMCTS: A scalable approach for general game learning'. Together they form a unique fingerprint.

Cite this