An Architecture for Learning Agents

This paper contains a proposal of an architecture for learning agents. The architecture supports centralized learning. Learning may be performed by several agents in the system, but it should be independent (without communication or cooperation connected with the learning process). An agent may have several learning modules for different aspects of its activity. Each module can use different learning strategy. Application of the architecture is studied on example of Fish-Banks game simulator.

[1]  Michael Luck,et al.  A Direct Reputation Model for VO Formation , 2005, CEEMAS.

[2]  Janusz Wojtusiak,et al.  AQ21 USER 'S GUIDE , 2004 .

[3]  Leonid Sheremetov,et al.  Weiss, Gerhard. Multiagent Systems a Modern Approach to Distributed Artificial Intelligence , 2009 .

[4]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[5]  Bartlomiej Sniezynski,et al.  Learning in a Multi-agent Approach to a Fish Bank Game , 2005, CEEMAS.

[6]  Toshiharu Sugawara,et al.  On-Line Learning of Coordination Plans , 1993 .

[7]  G. Hardin,et al.  The Tragedy of the Commons , 1968, Green Planet Blues.

[8]  Ryszard S. Michalski,et al.  AQVAL/1 (AQ7) User's Guide and Program Description , 1975 .

[9]  Jack Dongarra,et al.  Computational Science - ICCS 2007, 7th International Conference, Beijing, China, May 27 - 30, 2007, Proceedings, Part III , 2007, ICCS.

[10]  Bartlomiej Sniezynski,et al.  Resource Management in a Multi-agent System by Means of Reinforcement Learning and Supervised Rule Learning , 2007, International Conference on Computational Science.

[11]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[12]  Yves Demazeau,et al.  Multy-agent System to Model the Fish Banks Game Process , 1999, CEEMAS.

[13]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[14]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[15]  Sandip Sen,et al.  Learning in multiagent systems , 1999 .