Portal de Periódicos da CAPES

Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics

2021; Multidisciplinary Digital Publishing Institute; Volume: 11; Issue: 5 Linguagem: Inglês

10.3390/app11052056

2076-3417

Alba Cotarelo, Vicente García‐Díaz, Edward Rolando Núñez‐Valdéz, Cristian González García, Alberto Gómez Gómez, Jerry Chun‐Wei Lin,

Gambling Behavior and Treatments

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.