This paper describes a reinforcement learning-based strategy developed for Robocup simulator league competition. In overview: each agent is provided a common set of skills (motor schema-based behavioral assemblages) from which it builds a task-achieving strategy using reinforcement learning. The agents learn individually to activate particular behavioral assemblages given their current situation and a reward signal. The entire team is jointly rewarded or penalized when they score or are scored against (global reinforcement). This approach provides for diversity in individual behavior.
CITATION STYLE
Balch, T. (1998). Integrating learning with motor schema-based control for a Robot Soccer Team (pp. 483–491). https://doi.org/10.1007/3-540-64473-3_86
Mendeley helps you to discover research relevant for your work.