Peter Stone's Selected Publications

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


ATT-CMUnited-2000: Third Place Finisher in the RoboCup-2000 Simulator League

Patrick Riley, Peter Stone, David McAllester, and Manuela Veloso. ATT-CMUnited-2000: Third Place Finisher in the RoboCup-2000 Simulator League. In P. Stone, T. Balch, and G. Kraetzschmar, editors, RoboCup-2000: Robot Soccer World Cup IV, Lecture Notes in Artificial Intelligence, Springer Verlag, Berlin, 2001.

Download

[PDF]114.6kB  [postscript]82.2kB  

Abstract

The ATT-CMUnited-2000 simulator team finished in third place at Robocup-2000. It was one of only three teams to finish ahead of the previous year's champion, CMUnited-99. ATT-CMUnited-2000 is based upon CMUnited-99, which in turn is is based on CMUnited-98. In particular, it uses all of the techniques embodied in the previous teams, including: (1) Hierarchical machine learning (Layered learning); (2) Flexible, adaptive formations (Locker-room agreement); (3) Single-channel, low-bandwidth communication; (4) Predictive, locally optimal skills (PLOS); (5) Strategic positioning using attraction and repulsion (SPAR). Our goal in creating ATT-CMUnited-2000 was to investigate new research directions.

BibTeX Entry

@InCollection(LNAI2000-team,
  Author =       "Patrick Riley and Peter Stone and David McAllester and Manuela Veloso",
  Title =        "{ATT}-{CMU}nited-2000: Third Place Finisher in the {R}obo{C}up-2000 Simulator League",
  booktitle =    "{R}obo{C}up-2000: Robot Soccer World Cup {IV}",
  Editor =       "P. Stone and T. Balch and G. Kraetzschmar",
  Publisher =    "Springer Verlag",
  series="Lecture Notes in Artificial Intelligence",
  volume="2019",
  address =      "Berlin",
  year =         2001,
  abstract = {              
              The ATT-CMUnited-2000 simulator team finished in third
              place at Robocup-2000.  It was one of only three teams
              to finish ahead of the previous year's champion,
              CMUnited-99.
              ATT-CMUnited-2000 is based upon CMUnited-99, which in
              turn is is based on CMUnited-98. In particular, it uses
              all of the techniques embodied in the previous teams,
              including: (1) Hierarchical machine learning (Layered
              learning); (2) Flexible, adaptive formations
              (Locker-room agreement); (3) Single-channel,
              low-bandwidth communication; (4) Predictive, locally
              optimal skills (PLOS); (5) Strategic positioning using
              attraction and repulsion (SPAR).
              Our goal in creating ATT-CMUnited-2000 was to
              investigate new research directions.},

Generated by bib2html.pl (written by Patrick Riley ) on Wed Jul 09, 2014 11:54:44