next up previous
Next: Introduction

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

Peter Stone and Manuela Velosogif
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
{pstone,veloso}@cs.cmu.edu
http://www.cs.cmu.edu/{"7E pstone,"7E mmv}

Running title: Soccer: Collaborative and Adversarial

Abstract:

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.





Peter Stone
Thu Aug 22 12:51:13 EDT 1996