Collaborative Learning Agents with Structural Classifier Systems

Abstract

We propose a new learning agent architecture for collaborative learning. To learn any complicated task in multi-agent environment, simple reinforcement architectures have limitations on learning. Therefore, we propose splitting learning mechanism into three separate layers to learn required behavior, which are respectively organized by the Classifier… (More)

Topics

2 Figures and Tables

Cite this paper

@inproceedings{Chikara1999CollaborativeLA, title={Collaborative Learning Agents with Structural Classifier Systems}, author={Maezawa Chikara and Atsumi Masayasu}, booktitle={GECCO}, year={1999} }