Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics
Cotarelo, Alba; García-Díaz, Vicente; Núñez-Valdez, Edward Rolando; García, Cristian González; Gomez, Alberto; Lin, Jerry Chun-Wei
Peer reviewed, Journal article
Published version
Permanent lenke
https://hdl.handle.net/11250/2983539Utgivelsesdato
2021Metadata
Vis full innførselSamlinger
Originalversjon
Cotarelo, A., García-Díaz, V., Núñez-Valdez, E. R., González García, C., Gómez, A., & Chun-Wei Lin, J. (2021). Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics. Applied Sciences, 11(5):2056. 10.3390/app11052056Sammendrag
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.