Analyzing and taming collective learning of a multiagent system with connected replicator dynamics

Authors:
Masaaki Kunigami;Takao Terano
Affiliations:
Graduate School of Business Science, Tsukuba University, Tokyo, Japan;Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan
Venue:
JSAI'03/JSAI04 Proceedings of the 2003 and 2004 international conference on New frontiers in artificial intelligence
Year:
2003

Citing 0
Cited 1

Evolutionary dynamics for designing multi-period auctions

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 3

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper analyzes complex collective behaviors of a multiagent system, which consists of interacting agents with evolutionary learning capabilities. The interaction and learning of the agents are modeled by the concept of Connected Replicator Dynamics expanded from evolutionary Game Theory. The dynamic learning system we analyze shows various behavioral and decision changes including bifurcation of chaos in the sense of physical sciences. The main contributions of the paper are summarized as follows: (1) In amultiagent system, the emergence of chaotic behaviors is general and essential, even if each agent does not have chaotic properties; and (2) However, a simple controlling agent with the Keep-It-Simple-Stupid (KISS) principle, or a sheep-dog agent, is able to domesticate or tame the complex behaviors.