Emergence of Cooperation in a Multiple Predator, Single Prey Game

May 2003

Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2003)

Volume

Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2003)

All Papers

This research concerns the comparison of three different artificial evolution approaches for the design of cooperative behavior in a group of simulated mobile robots. The first and second approaches, termed: single pools and plasticity, are characterized by robots that share a single genotype, though the plasticity approach includes a learning mechanism. The third approach, termed: multiple pools, is characterized by robots that use different genotypes. The application domain is a pursuit-evasion game in which a team of robots, termed: predators, collectively work to capture or slow a single robot, termed: the prey. Results indicate that the multiple pools approach is superior comparative to the other two approaches in deriving robust and consistently effective prey-capture strategies, given that this approach facilitates the evolution of specialized behavioral roles in the predator team.