Cooperative Coevolution of Multi-Agent Systems
Active from 2000 - 2007

The Enforced Subpopulations (ESP) method can be extended to evolving multiple networks simultaneously, and applied to multi-agent problem solving tasks. In the prey capture domain, multiple predators evolved to perform different and compatible roles, so that the whole team of predators efficiently captured the prey. Remarkably, multi-agent evolution was more efficient than evolving a central controller for the task. Also, the predators did not need to communicate or even know the other predators' locations; role-based cooperation was highly efficient in this task. Communication would result in more general, but less effective, behavior. These results suggest that multi-agent neuroevolution is a promising approach for complex real-world tasks. We are currently working on applying it to other multi-agent games.

One such multi-agent task to which neuroevolution has been successfully applied is the domain of robot soccer. Here is a summary of work that describes how three different learning methods compare in two versions of the robot soccer keepaway domain.

Nate Kohl Ph.D. Alumni nate [at] natekohl net
Shimon Whiteson Former Collaborator s a whiteson [at] uva nl
Chern Han Yong Masters Alumni cherny [at] nus edu sg
The Evolution of Coordinated Cooperative Behaviors Padmini Rajagopalan PhD Thesis, Department of Computer Science, University of Texas at Austin, Austin, TX, August 2016. 2016

Multiagent Learning through Neuroevolution Risto Miikkulainen, Eliana Feasley, Leif Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, an... In J. Liu et al., editors, Advances in Computational Intelligence, LNCS 7311, 24-46, Berlin, ... 2012

Coevolution of Role-Based Cooperation in Multi-Agent Systems Chern Han Yong and Risto Miikkulainen Technical Report AI07-338, Department of Computer Sciences, The University of Texas at Austin, 2007. 2007

Cooperative Coevolution Of Multi-Agent Systems Chern Han Yong and Risto Miikkulainen Technical Report AI07-338, Department of Computer Sciences, The University of Texas at Austin, 2001. 2001

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