Layered Learning In Multiagent Systems: A Winning Approach To Robotic Soccer (Intelligent Robotics And Autonomous Agents),Used

This book looks at multiagent systems that consist of teams of autonomous agents acting in realtime, noisy, collaborative, and adversarial environments.This book looks at multiagent systems that consist of teams of autonomous agents acting in realtime, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a generalpurpose machinelearning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machinelearning methods. Third, the book introduces a new multiagent reinforcement learning algorithmteampartitioned, opaquetransition reinforcement learning (TPOTRL)designed for domains in which agents cannot necessarily observe the statechanges caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a realtime, noisy domain with teammates and adversariesa computersimulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 1100.