The Anticipatory Classiier System and Genetic Generalization the Anticipatory Classiier System and Genetic Generalization
It is shown that it is possible to form a symbiosis between a directed specialization and a genetic generalization mechanism achieving a learning mechanism that evolves a complete, accurate, and compact description of a perceived environment.
Abstract
The anticipatory classiier system (ACS) combines the learning classi-er system framework with the learning theory of anticipatory behavioral control. The result is an evolutionary system that builds an environmental model and further applies reinforcement learning techniques to form an optimal behavioral policy in the model. After providing some background as well as outlining the objectives of the system, we explain in detail all involved current processes. Furthermore, we analyze the deeciency of over-specialization in the anticipatory learning process (ALP), the main learning mechanism in the ACS. Consequently, we introduce a genetic algorithm (GA) to the ACS that is meant for generalization of over-specialized clas-siiers. We show that it is possible to form a symbiosis between a directed specialization and a genetic generalization mechanism achieving a learning mechanism that evolves a complete, accurate, and compact description of a perceived environment. Results in three diierent environmental settings connrm the usefulness of the genetic algorithm in the ACS. Finally, we discuss future research directions with the ACS and anticipatory systems in general.