Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics

Applied Sciences

Alberto Gómez¹  Jerry Chun-Wei Lin²  Alba Cotarelo³  Cristian González García³  Vicente García-Díaz³  EdwardRolando Núñez-Valdez³ 

[1] Department of Business Organization, University of Oviedo, 33003 Oviedo, Spain;Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, 5063 Bergen, Norway;Department of Computer Science, University of Oviedo, 33003 Oviedo, Spain;

关键词: Monte Carlo tree search;    Neural Networks;    generalized implementation;    Dots and Boxes;   

DOI  :  10.3390/app11052056

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown