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.

PDF, PS, HTML

In RoboCup-2000: Robot Soccer World Cup IV, P. Stone and T. Balch and G. Kraetzschmar (Eds.), Vol. 2019, Berlin 2001. Springer Verlag.

@InCollection{LNAI2000-team, title={ATT-CMUnited-2000: Third Place Finisher in the RoboCup-2000 Simulator League}, author={Patrick Riley and Peter Stone and David McAllester and Manuela Veloso}, booktitle={RoboCup-2000: Robot Soccer World Cup IV}, volume={2019}, editor={P. Stone and T. Balch and G. Kraetzschmar}, series={Lecture Notes in Artificial Intelligence}, address={Berlin}, publisher={Springer Verlag}, url="http://www.cs.utexas.edu/users/ai-lab?LNAI2000-team", year={2001} }