A model of Baldwin effect in populations of self-learning agents

A model of Baldwin effect in populations of self-learning agents

We study an evolution model of adaptive self-learning agents. The control system of agents is based on a neural network adaptive critic design. Each agent is a broker that predicts stock price changes and uses its predictions for action selection. The agent tries to get rich by buying and selling st...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Red'ko, V.G., Mosalov, O.P., Prokhorov, D.V.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Adaptive control
Adaptive systems
Bioinformatics
Control system synthesis
Control systems
Genetic mutations
Genomics
Neural networks
Organisms
Programmable control
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We study an evolution model of adaptive self-learning agents. The control system of agents is based on a neural network adaptive critic design. Each agent is a broker that predicts stock price changes and uses its predictions for action selection. The agent tries to get rich by buying and selling stocks. We demonstrate that the Baldwin effect takes place in our model, viz., originally acquired adaptive policy of an agent-broker becomes inherited in the course of the evolution. In addition, we compare agent behavioral tactics with searching behavior of simple animals.
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2005.1556071