Discovering Chinese Chess Strategies through Coevolutionary Approaches

Abstract

Coevolutionary techniques have been proven to be effective in evolving solutions to many game related problems, with successful applications in many complex chess-like games like Othello, Checkers and Western Chess. This paper explores the application of coevolutionary models to learn Chinese Chess strategies. The proposed Chinese Chess engine uses alpha-beta search algorithm, quiescence search and move ordering. Three different models are studied: single-population competitive, host-parasite competitive and cooperative coevolutionary models. A modified alpha-beta algorithm is also developed for performance evaluation and an archiving mechanism is implemented to handle intransitive behaviour. Interesting traits are revealed when the coevolution models are simulated under different settings - with and without opening book. Results show that the coevolved players can perform relatively well, with the cooperative model being best for finding good players under random strategy initialization and the host-parasite model being best for the case when strategies are initialized with a good set of starting seeds.