Wolfgang Stolzmann: Two Applications of Anticipatory Classifier Systems (ACSs)
Abstract: Anticipatory classifier systems (ACSs) are a new kind of classifier systems (CSs) that learn by using the cognitive mechanism of anticipatory behavioural control. At first this paper gives a brief introduction to ACSs. Then two applications of ACSs are discussed. The first one is a simulation of an experiment about latent learning in rats that was done by Seward (1949) and first simulated by Riolo (1991). The second one consists of a simulation of a robot that has to learn its eye-hand coordination, starting without any knowledge, that was described and simulated by Birk (1995) using Drescher's schemata (Drescher, 1991, p. 9).
Keywords: learning, classifier systems, anticipatory behavioral control
Published: Proceedings of the 2nd European Conference on Cognitive Science, pp. 68-73. Manchester, UK.
Erzeugt: 10.10.97; letzte Änderung: 9.6.98 / WST