Improving Coevolution by Random Sampling | dr hab. Wojciech Jaśkowski

by Wojciech Jaśkowski, Paweł Liskowski, Marcin Szubert, Krzysztof Krawiec

Abstract:

Recent developments cast doubts on the effectiveness of coevolutionary learning in interactive domains. A simple evolution with fitness evaluation based on games with random strategies has been found to generalize better than competitive coevolution. In an attempt to investigate this phenomenon, we analyze the utility of random opponents for one- and two-population competitive coevolution applied to learning strategies for the game of Othello. We show that if coevolution uses two-population setup and engages also random opponents, it is capable of producing equally good strategies as evolution with random sampling for the expected utility performance measure. To investigate the differences between analyzed methods, we introduce performance profile, a tool that measures the player’s performance against opponents of various strength. The profiles reveal that evolution with random sampling produces players coping well with mediocre opponents, but playing relatively poorly against stronger ones. This finding explains why in the round-robin tournament, evolution with random sampling is one of the worst methods from all those considered in this study.

View PDF

Reference:

Improving Coevolution by Random Sampling (Wojciech Jaśkowski, Paweł Liskowski, Marcin Szubert, Krzysztof Krawiec), In GECCO’13: Proceedings of the 15th annual conference on Genetic and Evolutionary Computation (Christian Blum, ed.), ACM, 2013.

Bibtex Entry:

@InProceedings{Jaskowski2013improving,
  Title                    = {Improving Coevolution by Random Sampling},
  Author                   = {Wojciech Jaśkowski and Pawe{ł} Liskowski and Marcin Szubert and Krzysztof Krawiec},
  Booktitle                = {GECCO'13: Proceedings of the 15th annual conference on Genetic and Evolutionary Computation},
  Year                     = {2013},

  Address                  = {Amsterdam, The Netherlands},
  Editor                   = {Christian Blum},
  Month                    = {July},
  Pages                    = {1141--1148},
  Publisher                = {ACM},

  Abstract                 = {Recent developments cast doubts on the effectiveness of coevolutionary learning in interactive domains. A simple evolution with fitness evaluation based on games with random strategies has been found to generalize better than competitive coevolution. In an attempt to investigate this phenomenon, we analyze the utility of random opponents for one- and two-population competitive coevolution applied to learning strategies for the game of Othello. We show that if coevolution uses two-population setup and engages also random opponents, it is capable of producing equally good strategies as evolution with random sampling for the expected utility performance measure.

To investigate the differences between analyzed methods, we introduce performance profile, a tool that measures the player's performance against opponents of various strength. The profiles reveal that evolution with random sampling produces players coping well with mediocre opponents, but playing relatively poorly against stronger ones. This finding explains why in the round-robin tournament, evolution with random sampling is one of the worst methods from all those considered in this study.},
  Keywords                 = {Competitive Coevolution, Solution Concepts, Othello, Maximization of Expected Utility, Strategy Learning, Performance Profile},
  Url                      = {http://www.cs.put.poznan.pl/mszubert/pub/jaskowski2013gecco.pdf}
}