An architecture for action selection in robotic soccer

Authors:
Peter Stone;David McAllester
Affiliations:
AT&T Labs -- Research, 180 Park Ave., Florham Park, NJ;AT&T Labs -- Research, 180 Park Ave., Florham Park, NJ
Venue:
Proceedings of the fifth international conference on Autonomous agents
Year:
2001

Citing 6
Cited 9

Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer

Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
RoboCup-99: Robot Soccer World Cup III

RoboCup-99: Robot Soccer World Cup III
AT Humboldt - Development, Practice and Theory

RoboCup-97: Robot Soccer World Cup I
Playing Soccer by Modifying and Combining Primitive Reactions

RoboCup-97: Robot Soccer World Cup I
The CMUnited-99 Champion Simulator Team

RoboCup-99: Robot Soccer World Cup III

Specifying Rational Agents with Statecharts and Utility Functions

RoboCup 2001: Robot Soccer World Cup V
RoboLog Koblenz 2001

RoboCup 2001: Robot Soccer World Cup V
Keepaway Soccer: A Machine Learning Testbed

RoboCup 2001: Robot Soccer World Cup V
ATTUnited-2001: Using Heterogeneous Players

RoboCup 2001: Robot Soccer World Cup V
Qualitative Velocity and Ball Interception

KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Evolving Soccer Keepaway Players Through Task Decomposition

Machine Learning
Balancing Gains, Risks, Costs, and Real-Time Constraints in the Ball Passing Algorithm for the Robotic Soccer

RoboCup 2006: Robot Soccer World Cup X
Probabilistic Decision Making in Robot Soccer

RoboCup 2007: Robot Soccer World Cup XI
Rational Passing Decision Based on Region for the Robotic Soccer

RoboCup 2007: Robot Soccer World Cup XI

Quantified Score

Hi-index	0.02

Visualization

Abstract

CMUnited-99 was the 1999 RoboCup robotic soccer simulator league champion. In the RoboCup-2000 competition, CMUnited-99 was entered again and despite being publicly available for the entire year, it still finished in 4th place. This paper presents some of the key elements behind \attcmunited, one of the three teams that finished ahead of CMUnited-99 in RoboCup-2000 out of thirty four entrants. Playing against CMUnited-99, \attcmunited\ scores an average of about 8 goals per opponent goal. This paper describes some of the key innovations that make this improvement possible.