论文信息 - CMUnited-98: RoboCup-98 Simulator World Champion Team

CMUnited-98: RoboCup-98 Simulator World Champion Team

The CMUnited-98 simulator team became the 1998 RoboCup simu lator league champion by winning all 8 of its games, outscoring opponents by a total of 66–0. CMUnit ed-98 builds upon the successful CMUnited-97 implementation, but also improves upon it in many ways. This article gives an overview of the CMUnited-98 agent skill and multi-agent coordination strategies, emphasizi ng the recent improvements.

Peter Stone | Manuela Veloso | Patrick Riley

[1] Manuela M. Veloso,et al. Team-partitioned, opaque-transition reinforcement learning , 1999, AGENTS '99.

[2] Lenka Lhotská,et al. Learning in Multi-Agent Systems: Theoretical Issues , 1997, EUROCAST.

[3] Ian Frank,et al. Soccer Server: A Tool for Research on Multiagent Systems , 1998, Appl. Artif. Intell..

[4] Manuela M. Veloso,et al. Layered Approach to Learning Client Behaviors in the Robocup Soccer Server , 1998, Appl. Artif. Intell..

[5] Manuela M. Veloso,et al. The CMUnited-97 Simulator Team , 1997, RoboCup.

[6] Manuela M. Veloso,et al. CMUNITED-97: RoboCup-97 Small-Robot World Champion Team , 1998, AI Mag..

[7] Manuela M. Veloso,et al. Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork , 1999, Artif. Intell..

[8] Hiroaki Kitano,et al. RoboCup: A Challenge Problem for AI , 1997, AI Mag..

[9] Manuela M. Veloso,et al. The CMUnited-98 Champion Simulator Team , 1998, RoboCup.