ABSTRACT
This article describes how racing procedures in evolution strategies can help reduce the number of evaluations. This idea is illustrated on learning Tetris players which can be addressed as a stochastic optimization problem. Different experiments show the benefits of the racing procedures in evolution strategies which can significantly reduce the number of evaluations.
- J.-Y. Audibert, R. Munos, and C. Szepesvári. Tuning bandit algorithms in stochastic environments. In M. H. et. al., editor, Algorithmic Learning Theory, volume 4754 of LNCS, pages 150--165. Springer, 2007. Google Scholar
- A. Boumaza. On the evolution of artificial tetris players. In Proceeding of the IEEE Symposium on Computational Intelligence and Games 2009 (CIG'9), pages 387--393. IEEE, June 2009. Google ScholarDigital Library
- C. P. Fahey. Tetris AI, Computer plays Tetris, 2003. On the web http://colinfahey.com/tetris/tetris_en.html.Google Scholar
- N. Hansen, S. Müller, and P. Koumoutsakos. Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary Computation, 11(1):1--18, 2003. Google ScholarDigital Library
- V. Heidrich-Meisner and C. Igel. Hoeffding and bernstein races for selecting policies in evolutionary direct policy search. In Proc. of the 26th ICML, pages 401--408, New York, 2009. ACM. Google ScholarDigital Library
- C. Thiery and B. Scherrer. Improvements on Learning Tetris with Cross Entropy. International Computer Games Association Journal, 32, 2009.Google Scholar
Index Terms
- Designing artificial tetris players with evolution strategies and racing
Recommendations
On the evolution of artificial Tetris players
CIG'09: Proceedings of the 5th international conference on Computational Intelligence and GamesIn the paper, we focus the use of evolutionary algorithms to learn strategies to play the game of Tetris. We describe the problem and discuss the nature of the search space. We present experiments to illustrate the learning process of our artificial ...
Reducing the learning time of tetris in evolution strategies
EA'11: Proceedings of the 10th international conference on Artificial EvolutionDesigning artificial players for the game of Tetris is a challenging problem that many authors addressed using different methods. Very performing implementations using evolution strategies have also been proposed. However one drawback of using evolution ...
Imitation-based evolution of artificial game players
Because of the rapid progress of commercial computer games in recent years the development of artificial characters that inhabit the presented game worlds has become a challenging task with very specific requirements. A particular computer game specific ...
Comments