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 best be evolved? When the agents are controlled with neural networks, a powerful method is to coevolve them in separate subpopulations, and test together in the common task. In this paper, such a method, called Multi-Agent ESP (Enforced Subpopulations) is presented, and demonstrated in a prey-capture task. The approach is shown to perform better than evolving a single central controller for all agents. The role of communication in such domains is also studied, and shown to be unnecessary and even detrimental if effective behavior in the task can be expressed as ro1e-based cooperation rather than synchronization.

PDF

Technical Report HR-00-01, Department of Computer Sciences, The University of Texas at Austin.

@techreport{yong:ugthesis00, title={Cooperative Coevolution of Multi-Agent Systems}, author={Chern Han Yong}, number={HR-00-01}, school={Department of Computer Sciences, The University of Texas at Austin}, institution={Department of Computer Sciences, The University of Texas at Austin}, type={Undergraduate Honors Thesis}, url="http://www.cs.utexas.edu/users/ai-lab?yong:ugthesis00", year={2000} }