Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics
Open Access
- 25 February 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (5) , 2056
Abstract
Monte Carlo Tree Search is one of the main search methods studied presently. It has demonstrated its efficiency in the resolution of many games such as Go or Settlers of Catan and other different problems. There are several optimizations of Monte Carlo, but most of them need heuristics or some domain language at some point, making very difficult its application to other problems. We propose a general and optimized implementation of Monte Carlo Tree Search using neural networks without extra knowledge of the problem. As an example of our proposal, we made use of the Dots and Boxes game. We tested it against other Monte Carlo system which implements specific knowledge for this problem. Our approach improves accuracy, reaching a winning rate of 81% over previous research but the generalization penalizes performance.Keywords
This publication has 35 references indexed in Scilit:
- Specialization of a UCT-Based General Game Playing Program to Single-Player GamesIEEE Transactions on Computational Intelligence and AI in Games, 2015
- An Automatically Generated Evaluation Function in General Game PlayingIEEE Transactions on Computational Intelligence and AI in Games, 2013
- Research and Implementation of Dots-and-Boxes Game SystemJournal of Software, 2012
- Monte-Carlo Tree Search in Settlers of Catan2010
- Best-first fixed-depth minimax algorithmsArtificial Intelligence, 1996
- An incremental negamax algorithmArtificial Intelligence, 1990
- An analysis of alpha-beta pruningArtificial Intelligence, 1975
- The Monte Carlo MethodJournal of the American Statistical Association, 1949
- Zur Theorie der GesellschaftsspieleMathematische Annalen, 1928
- “L'Arithmétique Amusante”Nature, 1895