| Abstract: |
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. |