Improving Generalization Performance in Co-Evolutionary Learning

Recently, the generalization framework in co-evolutionary learning has been theoretically formulated and demonstrated in the context of game-playing. Generalization performance of a strategy (solution) is estimated using a collection of random test strategies (test cases) by taking the average game outcomes, with confidence bounds provided by Chebyshev’s Theorem. Chebyshev’s bounds have the advantage that they hold for any distribution of game outcomes. However, such a distribution-free framework leads to unnecessarily loose confidence bounds. In this contribution, we take advantage of the near-Gaussian nature of average game outcomes and provide tighter bounds based on parametric testing. This enables us to use small samples of test strategies to guide and improve the co-evolutionary search. We demonstrate our approach in a series of empirical studies involving the iterated prisoner’s dilemma and the more complex Othello game in a competitive co-evolutionary learning setting....

• Type: Journal
• Year: 2012
• Where: TEC
• Authors: Siang Yew Chong, Peter Tino, Day Chyi Ku, Xin Yao
• Keywords: Formal Methods, Game Outcomes, Generalization Performance, Othello Game, TEC 2012