Bucket brigade performance: I. Long sequences of classifiers
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Technical Note: \cal Q-Learning
Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Organization Self-Design of Distributed Production Systems
IEEE Transactions on Knowledge and Data Engineering
A Study of Organizational Learning in Multi-Agent Sytems
ECAI '96 Selected papers from the Workshop on Distributed Artificial Intelligence Meets Machine Learning, Learning in Multi-Agent Environments
Properties of the Bucket Brigade
Proceedings of the 1st International Conference on Genetic Algorithms
Proceedings of the 6th International Conference on Genetic Algorithms
Adaptive load balancing: a study in multi-agent learning
Journal of Artificial Intelligence Research
Making Organizational Learning Operational: Implications from Learning Classifier Systems
Computational & Mathematical Organization Theory
Hi-index | 0.00 |
This paper proposes a novel evolutionary computation model:Organizational-Learning Oriented Classifier System (OCS), anddescribes its application to Printed Circuit Boards (PCBs) redesignproblems in a computer aided design (CAD). Using the conventionalCAD systems which explicitly decide the parts‘ placements by aknowledge base, the systems cannot effectively place the parts asdone by human experts. Furthermore, the supports of human expertsare intrinsically required to satisfy the constraints and tooptimize a global objective function. However, in theproposed model OCS, the parts generate and acquire adaptivebehaviors for an appropriate placement without explicit control. InOCS, we focus upon emergent processes in which the parts dynamicallyform an organized group with autonomously generating adaptivebehaviors through local interaction among them. Using the model OCS,we have conducted intensive experiments on a practical PCB redesignproblem for electric appliances. The experimental results haveshown that: (1) it has found the feasible solutions of the samelevel as the ones by human experts, (2) solutions are locallyoptimal, and also globally better than the ones by human expertswith regard to the total wiring length, and (3) the solutions aremore preferable than those in the conventional CAD systems.