Peter Stone's Selected Publications

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


A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server

Peter Stone and Manuela Veloso. A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server. Applied Artificial Intelligence, 12:165–188, 1998.
HTML version.

Download

[PDF]189.1kB  [postscript]1.2MB  

Abstract

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine Learning (ML) techniques to help build multiagent systems. Robotic soccer is a particularly good domain for studying MAS and Multiagent Learning. Our approach to using ML as a tool for building Soccer Server clients involves layering increasingly complex learned behaviors. In this article, we describe two levels of learned behaviors. First, the clients learn a low-level individual skill that allows them to control the ball effectively. Then, using this learned skill, they learn a higher-level skill that involves multiple players. For both skills, we describe the learning method in detail and report on our extensive empirical testing. We also verify empirically that the learned skills are applicable to game situations.

BibTeX Entry

@Article(AAI97, 
      Author="Peter Stone and Manuela Veloso",
      Title="A Layered Approach to Learning Client Behaviors in the {R}obo{C}up Soccer Server",  
      Journal="Applied Artificial Intelligence",   
      Year="1998",
      Volume="12",
      pages="165--188",
      abstract={
               In the past few years, Multiagent Systems (MAS) has
               emerged as an active subfield of Artificial
               Intelligence (AI).  Because of the inherent complexity
               of MAS, there is much interest in using Machine
               Learning (ML) techniques to help build multiagent
               systems.  Robotic soccer is a particularly good domain
               for studying MAS and Multiagent Learning.  Our approach
               to using ML as a tool for building Soccer Server
               clients involves layering increasingly complex learned
               behaviors.  In this article, we describe two levels of
               learned behaviors.  First, the clients learn a
               low-level individual skill that allows them to control
               the ball effectively.  Then, using this learned skill,
               they learn a higher-level skill that involves multiple
               players.  For both skills, we describe the learning
               method in detail and report on our extensive empirical
               testing.  We also verify empirically that the learned
               skills are applicable to game situations.
      },
      wwwnote={<a href="http://www.cs.utexas.edu/~pstone/Papers/97aai/final-learning.html">HTML version</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 05, 2014 13:23:01