Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer

Soccer is a rich domain for the study of multi-agent learning issues. Not only must the players learn to adapt to the behavior of different opponents, but they must learn to work together. We are using a robotic soccer system to study both adversarial and collaborative multi-agent learning issues. Here we briefly describe our experimental framework along with an initial learned behavior. We then discuss some of the issues that are arising as we extend our task to require collaborative and adversarial learning. Introduction Soccer is a rich domain for the study of multi-agent learning issues. Teams of players must work together in order to put the ball in the opposing goal while at the same time defending their own. Adaptive learning is essential in this task since the dynamics of the system can change radically as the opponents' behaviors change. The players must be able to adapt to new situations. Not only must the players learn to adapt to the behavior of different opponents, but t..