Title

The Effectiveness of using a Historical Sequence-based Predictor Algorithm in the First International RoShamboTournament

Document Type

Article

Publication Date

11-2014

Abstract

Games can be used as simulations to check the effectiveness and viability of an Artificial Intelligence technique. In this study, a competitive RoShamBo AI is developed and its performance is measured using the first International RoShamBo Tournament test suite. The AI stores a history of its opponent's move and checks for repetition to predict the opponent's next play. A training program was also developed that finds the best performing bot variant by changing the bot's behavior in terms of increasing the history's window size. The developed AI is shown to rank high in the competition. This indicates the potential of using the core technique (of the proposed variant) as an Artificial Intelligence bot to similarly applicable games.

Share

COinS