Coevolution of Role-Based Cooperation in Multi-Agent Systems (2007)
In certain tasks such as pursuit and evasion, multiple agents need to coordinate their behavior to achieve a common goal. An interesting question is, how can such behavior be best evolved? A powerful approach is to control the agents with neural networks, coevolve them in separate subpopulations, and test them together in the common task. In this paper, such a method, called Multi-Agent ESP (Enforced SubPopulations), is proposed and demonstrated in a prey-capture task. First, the approach is shown more efficient than evolving a single central controller for all agents. Second, cooperation is found to be most efficient through stigmergy, i.e. through role-based responses to the environment, rather than direct communication between the agents. Together these results suggest that role-based cooperation is an effective strategy in certain multi-agent domains. [ This paper is a revision of AI01-287. ]
View:
PDF
Citation:
Technical Report AI07-338, Department of Computer Sciences, The University of Texas at Austin.
Bibtex:

Risto Miikkulainen Faculty risto [at] cs utexas edu
Chern Han Yong Masters Alumni cherny [at] nus edu sg
Chern Han Yong Masters Alumni cherny [at] nus edu sg
ESP JAVA 1.1 The ESP package contains the source code for the Enforced Sup-Populations system written in Java. This package is a near... 2002

ESP C++ The ESP package contains the source code for the Enforced Sup-Populations system written in C++. ESP is an extension t... 2000