Selection of Suitable Evaluation Function Based on Win/Draw Parameter in Othello

Abstract

Computer games have made their presence vocal by making themselves present in the homes and industry. Games have emerged to provide a simulated experience of the outdoor games with ease and customization. Another class of games come into play when the indoor games are played without any physical opponent. In such case computer itself takes the responsibility of being an opponent and tests the human intelligence. Board games are especially very popular to be played on computer with computer as an opponent. This paper discusses on of the board games: Othello. The game of Othello has proved its prominence by being an active research area since long time now and has been successful to grab extensive focus of researchers, knowledge engineers and game developers. Othello is not as simple as Checkers and not as complex as Chess: both in its execution time and complexity, therefore it is an appropriate choice to be considered as a benchmark in the games development. Finding a better evaluation function to implement Othello has been an open question of research since long. In this paper we have compared different available strategies at length. Extensive experimentation (approaching to 144,000 experiments collectively) has been done to measure the effectiveness of each evaluation function. After thorough experimentation it is proved that Multi Layer Perceptron Neural Network (MLPNN) is the best strategy among available with respect to its win/draw comparisons. As winning a game in slightly more time is considered to be effective instead of losing it quickly.