Intelligent Agents for the Game of Go

Jean-Baptiste Hoock 1, 2 Chang-Shing Lee 3 Arpad Rimmel 2 Fabien Teytaud 1, 2 Olivier Teytaud 1, 2 Mei-Hui Wang 4
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Monte-Carlo Tree Search (MCTS) is a very efficient recent technology for games and planning, par- ticularly in the high-dimensional case, when the number of time steps is moderate and when there is no natural evaluation function. Surprisingly, MCTS makes very little use of learning. In this paper, we present four techniques (ontologies, Bernstein races, Contextual Monte-Carlo and poolRave) for learning agents in Monte-Carlo Tree Search, and experiment them in difficult games and in particular, the game of Go.
Document type :
Journal articles
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download
Contributor : Jean-Baptiste Hoock <>
Submitted on : Wednesday, February 12, 2014 - 3:59:40 PM
Last modification on : Tuesday, April 10, 2018 - 3:26:01 PM
Long-term archiving on : Friday, July 15, 2011 - 2:47:59 AM


Files produced by the author(s)


  • HAL Id : inria-00544758, version 2



Jean-Baptiste Hoock, Chang-Shing Lee, Arpad Rimmel, Fabien Teytaud, Olivier Teytaud, et al.. Intelligent Agents for the Game of Go. IEEE Computational Intelligence Magazine, Institute of Electrical and Electronics Engineers, 2010. ⟨inria-00544758v2⟩



Record views


Files downloads