Introducing a genetic generalization pressure to the Anticipatory Classifier System - part 1: theoretical approach
Martin V. Butz, David E. Goldberg, Wolfgang Stolzmann · 2000
The Anticipatory Classifier System (ACS) is a learning classifier system that is based on the cognitive mechanism of anticipatory behavioral control. Besides the common reward learning, the ACS is able to learn latently (i.e. to learn without getting any reward) which is not possible with reinforcement learning techniques. Furthermore, it forms a complete internal representation of the environment and thus is able to use cognitive processes such as reasoning and planning. Latest research observed that the ACS is not generating accurate, maximally general rules reliably (i.e. rules which are accurate and also as general as possible), but it is sometimes generating over-specialized rules. This paper shows how a genetic algorithm can be used to overcome this present pressure of over-specialization in the ACS mechanism with a genetic generalization pressure. The ACS works then hybrid which learns latently, forms a cognitive map, and evolves accurate, maximally general rules.