Designing emergent cooperation: a pursuit–evasion game case study

Abstract

This research concerns a comparison of two neuroevolution approaches for the design of cooperative behavior in a group of simulated mobile robots. The first approach, termed single pool (SP), was characterized by robot neural controllers that were derived from a single genotype. The second approach, termed multiple pools (MP), was characterized by robot neural controllers that were derived from many different genotypes. The application domain implemented a pursuit–evasion game in which teams of robots of various sizes, termed predators, collectively worked to capture (immobilize) other robots, termed prey. The MP and SP approaches were tested, with and without lifetime learning, for the design of cooperative prey capture behavior within teams of predators. Results indicated that the MP approach was superior to the SP approach in terms of measures defined for prey-capture performance. Specifically, the MP approach facilitated behavioral specializations in the predator team facilitating emergent cooperative prey capture strategies that proved effective for the various team sizes tested.