The quantitative law of effect is a robust emergent property of an evolutionary algorithm for reinforcement learning

Authors:
J. J McDowell;Zahra Ansari
Affiliations:
Department of Psychology, Emory University, Atlanta, Georgia;Department of Psychology, Emory University, Atlanta, Georgia
Venue:
ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Year:
2005

Citing 5
Cited 1

Operant conditioning in skinnerbots

Adaptive Behavior - Special issue on environment structure and behavior
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Evolving Behavioural Choice: An Investigation into Herrnstein's Matching Law

ECAL '99 Proceedings of the 5th European Conference on Advances in Artificial Life
Modeling Group Foraging: Individual Suboptimality, Interference, and a Kind of Matching

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

Simple artificial neural networks that match probability and exploit and explore when confronting a multiarmed bandit

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An evolutionary reinforcement-learning algorithm, the operation of which was not associated with an optimality condition, was instantiated in an artificial organism. The algorithm caused the organism’s behavior to evolve in response to selection pressure applied by reinforcement from the environment. The resulting behavior was consistent with the well-established quantitative law of effect, which asserts that the time rate of a behavior is a hyperbolic function of the time rate of reinforcement obtained for the behavior. The high-order, steady-state, hyperbolic relationship between behavior and reinforcement exhibited by the artificial organism did not depend on specific qualitative or quantitative features of the evolutionary algorithm, and it described the organism’s behavior significantly better than other, similar, function forms. This evolutionary algorithm is a good candidate for a dynamics of live behavior, and it might be a useful building block for more complex artificial organisms.