Wolfgang Stolzmann, Martin V. Butz, Joachim Hoffmann & David E. Goldberg:
First Cognitive Capabilities in the Anticipatory Classifier System
This paper adds a new viewpoint to the Anticipatory Classifier System (ACS). It approaches the system from a psychological perspective and thus provides new insights to the current system. By simulating previously published rat experiments, the paper compares the behavior of the ACS with the behabior of the rats. Two further cognitive mechanisms are introduced to the ACS resulting in an animal-like behavior in the presented simulations. Moreover, the paper gives empirical evidence that the evolving generalized, internal environmental model is usable in the ACS for the mental adaptation of actions and thus enables reinforcement learning by mental simulation.
In: From Animals to Animats: Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior.
generated: 24 February 2000; last update: 24 February 2000 / WST