Daniel Polani
Johannes Gutenberg-Universität Mainz, Germany
Thomas Uthmann
Johannes Gutenberg-Universität Mainz, Germany
Download article
Published in: RobocCup-99 Team Descriptions. Simulation League
Linköping Electronic Conference Proceedings 4:18, p. 84-87
Linköping Electronic Articles in Computer and Information Science vol. 4 4:18, p. 84-87
Published: 1999-12-15
ISBN:
ISSN: 1650-3686 (print), 1650-3740 (online)
The development of our team for RoboCup~99 is mainly oriented towards a transparent way of transferring explicit knowledge into the agent control and its combination with learning algorithms capable of fine-tuning the acquired skills. The explicit knowledge is formulated in terms of rules; the non-explicit knowledge is to be realized as a set of parameters adapted by hierarchical reinforcement learning and by rule evolution. The teaching process for the implicit learning is not determined by a simple fixed reinforcement return; but by a --- possibly complex --- agent that represents a human or an automated coach.
[1] T. G. Dietterich. Hierarchical reinforcement learning with the MAXQ value function decomposition. Submitted to Machine Learning; 1999.
[2] G. Edelman. Neural Darwinism: Theory of Neuronal Group Selection. Basic Books; New York; 1987.
[3] Leslie Pack Kaelbling; Michael L. Littman; and Andrew W. Moore. Reinforcement learning: a survey. Journal of Arti cial Intelligence Research; 4:237-285; May 1996.
[4] Hitoshi Matsubara; Itsuki Noda; and Kazuo Hiraki. Learning of cooperative actions in multi-agent systems: a case study of pass in soccer. In AAAI-96 Spring Symposium on Adaptation; Coevolution and Learning in Multi-Agent Systems; pages 63-67; Mar 1996.
[5] D. Moriarty and R. Miikkulainen. Forming neural networks through ecient and adaptive co-evolution. Evolutionary Computation; 5:373- 399; 1997.
[6] D. Polani and R. Miikkulainen. Fast reinforcement learning through eugenic neuro-evolution. Technical Report AI99-277; Department of Computer Sciences; The University of Texas at Austin; January 1999.
[7] R. S. Sutton and A. G. Barto. Reinforcement Learning. Bradford; 1998.
