Sandip Sen helped establish multi-agent learning as a coordination problem, studying how adaptive agents can learn complementary behavior, reciprocity, cooperation, and trust.
Peter Stone used RoboCup's noisy, real-time soccer environment to study layered learning, flexible roles, limited communication and collaboration among agents that must cooperate with teammates while competing against opponents.
Manuela Veloso used robotic soccer and collaborative robots as experimental laboratories for coordination, learning, role assignment and communication among autonomous agents.