Abstract
We review an experiment in co-evolutionary learning of game playing where we show experimental evidence that the straightforward composition of individually learned models more often than not results in diluting what was earlier learned and that self-playing can result in reaching plateaus of un-interesting playing behavior. These observations suggest that learning cannot be easily distributed when one hopes to harness multiple experts to develop a quality computer player and reinforce the need to develop tools that facilitate the mix of expert-based tuition and computer self-learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Shannon, C.: Programming a computer for playing chess. Philosophical Magazine 41(4), 265–275 (1950)
Samuel, A.: Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development 3, 210–229 (1959)
Hsu, F.-H.: Behind Deep Blue: Building the Computer that Defeated the World Chess Champion. Princeton University Press, Princeton (2002)
Schaeffer, J., Bjoernsson, Y., Burch, N., Kishimoto, A., Mueller, M., Lake, R., Lu, P., Sutphen, S.: Solving Checkers. In: International Joint Conference on Artificial Intelligence (2005)
Kalles, D., Kanellopoulos, P.: On Verifying Game Design and Playing Strategies using Reinforcement Learning. In: ACM Symposium on Applied Computing, special track on Artificial Intelligence and Computation Logic, Las Vegas (2001)
Sutton, R.: Learning to Predict by the Methods of Temporal Differences. Machine Learning 3(1), 9–44 (1988)
Sutton, R., Barto, A.: Reinforcement Learning - An Introduction. MIT Press, Cambridge (1988)
Tesauro, G.: Temporal Difference Learning and TD-Gammon. Communications of the ACM 38(3), 58–68 (1995)
Littman, M.L.: Markov Games as a Framework for Multi-Agent Reinforcement Learning. In: 11th International Conference on Machine Learning, San Francisco, pp. 157–163 (1994)
Kalles, D., Ntoutsi, E.: Interactive Verification of Game Design and Playing Strategies. In: IEEE International Conference on Tools with Artificial Intelligence, Washington D.C. (2002)
Kalles, D.: Player co-modelling in a strategy board game: discovering how to play fast. Cybernetics and Systems 39(1), 1–18 (2008)
Kalles, D., Kanellopoulos, P.: A Minimax Tutor for Learning to Play a Board Game. In: 18th European Conference on Artificial Intelligence, workshop on Artificial Intelligence in Games, Patras, Greece, pp. 10–14 (2008)
Nicolescu, M.N., Matarić, M.J.: Natural methods for robot task learning: Instructive demonstrations, generalization and practice. In: 2nd International Conference on Autonomous Agents and Multi-Agent Systems, Melbourne, pp. 241–248 (2003)
Kaplan, F., Oudeyer, P.-Y., Kubinyi, E., Miklosi, A.: Robotic Clicker Training. Robotics and Autonomous Systems 38(3–4), 197–206 (2002)
Kalles, D.: Measuring Expert Impact on Learning how to Play a Board Game. In: 4th IFIP Conference on Artificial Intelligence Applications and Innovations, Athens, Greece (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kalles, D., Fykouras, I. (2010). Time Does Not Always Buy Quality in Co-evolutionary Learning. In: Konstantopoulos, S., Perantonis, S., Karkaletsis, V., Spyropoulos, C.D., Vouros, G. (eds) Artificial Intelligence: Theories, Models and Applications. SETN 2010. Lecture Notes in Computer Science(), vol 6040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12842-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-12842-4_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12841-7
Online ISBN: 978-3-642-12842-4
eBook Packages: Computer ScienceComputer Science (R0)