Title :
Learning classifier systems in multi-agent environments
Author :
Serendynski, F. ; Cichosz, P. ; Klebus, G.P.
Author_Institution :
Polish Acad. of Sci., Warsaw, Poland
Abstract :
The paper is devoted to the problem of learning decision policies in multi-agent games. We describe a general framework for studying games of intelligent agents, extending the basic model of games with limited interactions, and its specific realization based on learning classifier systems. Simulation results are presented that illustrate the convergence properties of the resulting system. Avenues for future work in this area are outlined
Keywords :
cooperative systems; game theory; learning (artificial intelligence); optimisation; classifier systems learning; convergence properties; decision policies; intelligent agents; multi-agent environments; simulation results;
Conference_Titel :
Genetic Algorithms in Engineering Systems: Innovations and Applications, 1995. GALESIA. First International Conference on (Conf. Publ. No. 414)
Conference_Location :
Sheffield
Print_ISBN :
0-85296-650-4
DOI :
10.1049/cp:19951064
