Between Teaching and Learning: Development of the Team ’Mainz Rolling Brains’ for the Simulation League of RoboCup ’99 Mainz-Rolling-Brains

The development of our team for RoboCup ’99 is mainly oriented towards a transparent way of transferring explicit knowledge into the agent control and its combination with learning algorithms capable of fine-tuning the acquired skills. The explicit knowledge is formulated in terms of rules, the non-explicit knowledge is to be realized as a set of parameters adapted by hierarchical reinforcement learning and by rule evolution. The teaching process for the implicit learning is not determined by a simple fixed reinforcement return, but by a — possibly complex — agent that represents a human or an automated coach.