Multi-Criteria Comparison of Coevolution and Temporal Difference Learning on Othello

  • Wojciech JaśkowskiEmail author
  • Marcin Szubert
  • Paweł Liskowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8602)


We compare Temporal Difference Learning (TDL) with Coevolutionary Learning (CEL) on Othello. Apart from using three popular single-criteria performance measures: (i) generalization performance or expected utility, (ii) average results against a hand-crafted heuristic and (iii) result in a head to head match, we compare the algorithms using performance profiles. This multi-criteria performance measure characterizes player’s performance in the context of opponents of various strength. The multi-criteria analysis reveals that although the generalization performance of players produced by the two algorithms is similar, TDL is much better at playing against strong opponents, while CEL copes better against weak ones. We also find out that the TDL produces less diverse strategies than CEL. Our results confirms the usefulness of performance profiles as a tool for comparison of learning algorithms for games.


Reinforcement learning Coevolutionary algorithm Reversi Othello Board evaluation function Weighted piece counter Interactive domain 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lucas, S.M., Runarsson, T.P.: Temporal difference learning versus co-evolution for acquiring othello position evaluation. In: IEEE Symposium on Computational Intelligence and Games, 52–59 IEEE (2006)Google Scholar
  2. 2.
    van den Dries, S., Wiering, M.A.: Neural-Fitted TD-Leaf Learning for Playing Othello With Structured Neural Networks. IEEE Transactions on Neural Networks and Learning Systems 23(11), 1701–1713 (2012)CrossRefGoogle Scholar
  3. 3.
    Szubert, M., Jaśkowski, W., Krawiec, K.: On scalability, generalization, and hybridization of coevolutionary learning: a case study for othello. IEEE Transactions on Computational Intelligence and AI in Games 5(3), 214–226 (2013)CrossRefGoogle Scholar
  4. 4.
    Axelrod, R.: The evolution of strategies in the iterated prisoner’s dilemma. In: Davis, L., (ed.) Genetic Algorithms in Simulated Annealing, London pp. 32–41 (1987)Google Scholar
  5. 5.
    Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine learning 3(1), 9–44 (1988)Google Scholar
  6. 6.
    Sutton, R., Barto, A.: Reinforcement learning, Vol. 9. MIT Press (1998)Google Scholar
  7. 7.
    Szubert, M., Jaśkowski, W., Krawiec, K.: Learning board evaluation function for othello by hybridizing coevolution with temporal difference learning. Control and Cybernetics 40(3), 805–831 (2011)MathSciNetGoogle Scholar
  8. 8.
    Lucas, S.M.: Learning to play Othello with N-tuple systems. Australian Journal of Intelligent Information Processing Systems, Special Issue on Game Technology 9(4), 01–20 (2007)Google Scholar
  9. 9.
    Darwen, P.J.: Why co-evolution beats temporal difference learning at backgammon for a linear architecture, but not a non-linear architecture. In: Proceedings of the 2001 Congress on Evolutionary Computation, Vol. 2, pp. 1003–1010. IEEE (2001)Google Scholar
  10. 10.
    Jaśkowski, W., Liskowski, P., Szubert, M., Krawiec, K.: Improving coevolution by random sampling. In: Blum, C. (ed.) GECCO’13: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, pp. 1141–1148. ACM, Amsterdam (2013)Google Scholar
  11. 11.
    Popovici, E., Bucci, A., Wiegand, R.P., de Jong, E.D.: Coevolutionary Principles. In: Handbook of Natural Computing. Springer (2011)Google Scholar
  12. 12.
    Nolfi, S., Floreano, D.: Coevolving Predator and Prey Robots: Do Arms Races Arise in Artificial Evolution? Artificial Life 4(4), 311–335 (1998)CrossRefGoogle Scholar
  13. 13.
    Tesauro, G.: Temporal difference learning and td-gammon. Communications of the ACM 38(3), 58–68 (1995)CrossRefGoogle Scholar
  14. 14.
    Chong, S.Y., Tino, P., Yao, X.: Relationship between generalization and diversity in coevolutionary learning. IEEE Transactions on Computational Intelligence and AI in Games 1(3), 214–232 (2009)CrossRefGoogle Scholar
  15. 15.
    Baker, J.E.: Reducing bias and inefficiency in the selection algorithms (1985)Google Scholar
  16. 16.
    Chong, S.Y., Tino, P., Ku, D.C., Xin, Y.: Improving Generalization Performance in Co-Evolutionary Learning. IEEE Transactions on Evolutionary Computation 16(1), 70–85 (2012)CrossRefGoogle Scholar
  17. 17.
    Szubert, M., Jaśkowski, W., Krawiec, K.: Coevolutionary temporal difference learning for othello. In: IEEE Symposium on Computational Intelligence and Games, Milano, Italy, pp. 104–111 (2009)Google Scholar
  18. 18.
    Samothrakis, S., Lucas, S., Runarsson, T., Robles, D.: Coevolving Game-Playing Agents: Measuring Performance and Intransitivities. IEEE Transactions on Evolutionary Computation 99, 1–15 (2012)Google Scholar
  19. 19.
    Comaniciu, D., Meer, P., Member, S.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603–619 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Wojciech Jaśkowski
    • 1
    Email author
  • Marcin Szubert
    • 1
  • Paweł Liskowski
    • 1
  1. 1.Institute of Computing SciencePoznan University of TechnologyPoznańPoland

Personalised recommendations