The sciences of the artificial (3rd ed.)
The sciences of the artificial (3rd ed.)
Cooperation without deliberation: a minimal behavior-based approach to multi-robot teams
Artificial Intelligence - Special issue on Robocop: the first step
Layered Learning and Flexible Teamwork in RoboCup Simulation Agents
RoboCup-99: Robot Soccer World Cup III
Behavior Classification with Self-Organizing Maps
RoboCup 2000: Robot Soccer World Cup IV
Communication and Coordination Among Heterogeneous Mid-Size Players: ART99
RoboCup 2000: Robot Soccer World Cup IV
Osaka University "Trackies 2001"
RoboCup 2001: Robot Soccer World Cup V
Hi-index | 0.00 |
Team strategy acquisition is one of the most important issues of multiagent systems, especially in an adversary environment. RoboCup has been providing such an environment for AI and robotics researchers. A deliberative approach to the team strategy acquisition seems useless in such a dynamic and hostile environment. This paper presents a learning method to acquire team strategy from a viewpoint of coach who can change a combination of players each of which has a fixed policy. Assuming that the opponent has the same choice for the team strategy but keeps the fixed strategy during one match, the coach estimates the opponent team strategy (player's combination) based on game progress (obtained and lost goals) and notification of the opponent strategy just after each match. The trade-off between exploration and exploitation is handled by considering how correct the expectation in each mode is. A case of 2 to 2 match was simulated and the final result (a class of the strongest combinations) was applied to RoboCup-2000 competition.