Title | ||
---|---|---|
Evolving Game Playing Strategies for Othello Incorporating Reinforcement Learning and Mobility. |
Abstract | ||
---|---|---|
Genetic programming is rapidly gaining popularity in research areas for the induction of complex game playing strategies for board games such as Othello, checkers, backgammon and chess endgames. Most of this research has focused on developing evaluation functions for use with standard game playing algorithms such as the alpha-beta algorithm or Monte Carlo tree search, supported by game specific knowledge bases. In previous work we have introduced a novel application of genetic programming to evolve game playing strategies composed of heuristics for board games. Each evolved strategy represents a player. Strategies are evolved in real time, during game play, while in other studies the strategies are generally created offline. The research presented in this paper builds on this work by investigating the use of reinforcement learning and mobility to further improve the evolved game playing strategies. An initial population of players created using the ramped half-and-half method is iteratively refined using reproduction, mutation and crossover. Tournament selection is used to choose parents. The board game Othello, also known as Reversi, is used to illustrate and evaluate this approach. The performance of the genetic programming approach incorporating reinforcement learning, the genetic programming approach incorporating mobility and the genetic programming approach incorporating both reinforcement learning and mobility were compared to that of the previous heuristic based approach. All three approaches were found to produce better results than the previous heuristic based approach, with the genetic programming approach incorporating just reinforcement learning performing the best. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1145/2815782.2815809 | SAICSIT Conf. |
Field | DocType | Citations |
Combinatorial game theory,Monte Carlo tree search,Game mechanics,Video game design,Computer science,Game design,Genetic programming,Artificial intelligence,Sequential game,Machine learning,Reinforcement learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Clive Frankland | 1 | 0 | 0.34 |
Nelishia Pillay | 2 | 237 | 33.72 |