Evolution of Goal-Directed Behavior Using Limited Information in a Complex Environment

July 1999

Evolution of Goal-Directed Behavior Using Limited Information in a Complex Environment

Authors:

Matthew Glickman and Katia Sycara

Abstract:

In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning effective behaviors in a complex environment that provides only limited perception and goal-feedback. Our specific approach evolves behavior in the form Artificial Neural Networks with recurrent connections. We apply our approach to learn effective behavior for a non-standard maze-navigation problem that is characterized by aspects of problems that are difficult to approach via other methods. Difficult aspects of the specified problem include the inability to sense all task-relevant state at any given time (the problem of "hidden state"), and limited feedback with respect to success or failure. We observe evolved networks to perform very well on the target problem. Further findings include adaptation to noise in action selection, performance proportional to memory capacity, and improved performance when network weights are transferred from training on one maze to another.
@conference{Glickman-1999-14951,
author = {Matthew Glickman And Katia Sycara},
title = {Evolution of Goal-Directed Behavior Using Limited Information in a Complex Environment},
booktitle = {Proceedings of 1st Annual Genetic and Evolutionary Computation Conference (GECCO '99)},
year = {1999},
month = {July},
pages = {1281 - 1288},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.