Learning team behaviors with adaptive heterogeneity
Liviu Panait · 2005
The task of hard-coding agent behaviors to achieve desired team behaviors is very difficult, if not intractable. The complexity of multiagent problems can also rise exponentially with the number of agents and their behavioral sophistication. The field of cooperative multiagent learning promises solutions to these issues by employing automatic search methods to discover agent behaviors, and as such it has been the focus of numerous studies in recent years.