|||Martin Spott, Martin Riedmiller, Improving a priori control knowledge by reinforcement learning, Proc. in AI: Fuzzy-Neuro-Systems '98, p. 146-153, Infix-Verlag, Mar 1998.
The major goal of the Fynesse control architecture is to combine the advantages of different modern controller design methods. A priori knowledge about the control strategy (classic controllers like PID, fuzzy controllers, statistical information) can be brought in if available. This information is transformed into a fuzzy relation. Advanced methods of dynamic programming are used to either improve existing control knowledge or to learn optimal control strategies from scratch. A neural network serves as a learning critic that evaluates the strategy represented by the fuzzy relation. At the end, the strategy can be interpreted in terms of fuzzy rules that are extracted from the fuzzy relation. This paper explains all design stages with the example of the cart pole balancing problem. It is especially shown that even simple controllers as a priori knowledge accelerate the learning procedure and improve the resulting quality of the controller considerably.