Learning Synthesis Schemes in Intelligent Systems

Lech Polkowski, Andrzej Skowron

We present a setting in which one can discuss problems of design, synthesis, analysis and control of complex systems by adaptive teams of intelligent distributed agents. We point to learning problems of this approach related to the necesity of extracting from the empirical data of constructs allowing the agents to negotiate their cooperative actions. We put our analysis into the framework of multistrategy learning (Michalski 1994) which combines empirical induction, abduction and reasoning by analogy in a hierarchical setting (Michalski 1994).

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.