Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


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

Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer.
Peter Stone and Manuela Veloso.
International Journal of Human-Computer Studies, 48(1):83–104, January 1998.
HTML version.

Download

[PDF]137.7kB  [postscript]3.2MB  

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.

BibTeX Entry

@Article(IJHCS,
        Author="Peter Stone and Manuela Veloso",
        Title= "Towards Collaborative and Adversarial Learning:  A Case Study in Robotic Soccer",
        Journal= "International Journal of Human-Computer
        Studies",year="1998",volume="48",number="1",month="January",
        pages="83--104",
        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.
        },
        wwwnote={<a href="http://www.cs.utexas.edu/~pstone/Papers/96ijhcs/article.html">HTML version</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Sun Nov 24, 2024 20:24:50