Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of different opponents. We are using a robotic soccer system to study these different types of multiagent learning: low-level skills, collaborative, and adversarial. Here we describe in detail our experimental framework. We present a learned, robust, low-level behavior that is necessitated by the multiagent nature of the domain, namely shooting a moving ball. We then discuss the issues that arise as we extend the learning scenario to require collaborative and adversarial learning.

PDF, PS, HTML

International Journal of Human-Computer Studies, 48(1):83-104, January 1998.

@Article{IJHCS, title={Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer}, author={Peter Stone and Manuela Veloso}, volume={48}, journal={International Journal of Human-Computer Studies}, number={1}, month={January}, pages={83-104}, url="http://nn.cs.utexas.edu/?IJHCS", year={1998} }