What a Neural Network Can Learn About Othello
A. Leouski, Paul E. Utgoff · 1996
Conventional Othello programs are based on a thorough analysis of the game, and typically employ sophisticated evaluation functions and supervised learning techniques that use large expert-labeled game databases. This paper presents an alternative method that trains a neural network to evaluate Othello positions via temporal difference (TD) learning. The approach is based on a network architecture that reflects the spatial and temporal organization of the problem domain. The network begins with random weights, and through self-play achieves an intermediate level of play. We also present a simple and effective method for analyzing what the network learned. 1 Introduction The game of Othello is a descendant of an old Japanese board game. Like chess, it is a deterministic, perfect information, zero-sum game of strategy between two players. The limited length of the game, typically sixty moves, and the small average branching factor, approximately seven, give Othello a complexity greater...