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
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
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
Hi-index | 0.02 |
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.