Evolving neural networks for strategic decision-making problems.

Full Abstract

Evolution of neural networks, or neuroevolution, has been a successful approach to many low-level control problems such as pole balancing, vehicle control, and collision warning. However, certain types of problems-such as those involving strategic decision-making-have remained difficult for neuroevolution to solve. This paper evaluates the hypothesis that such problems are difficult because they are fractured: The correct action varies discontinuously as the agent moves from state to state. A method for measuring fracture using the concept of function variation is proposed and, based on this concept, two methods for dealing with fracture are examined: neurons with local receptive fields, and refinement based on a cascaded network architecture. Experiments in several benchmark domains are performed to evaluate how different levels of fracture affect the performance of neuroevolution methods, demonstrating that these two modifications improve performance significantly. These results form a promising starting point for expanding neuroevolution to strategic tasks.

Author information

Author/s: Kohl, Nate (N); Miikkulainen, Risto (R);

Affiliation: Department of Computer Sciences, The University of Texas at Austin, 1 University Station C0500, Austin, TX, United States. nate(-atsign-)cs.utexas.edu

Journal and publication information

Publication Type: Journal Article

Journal: Neural networks : the official journal of the International Neural Network Society (Neural Netw), published in United States. (Language: eng)

Reference: 2009-Apr; vol 22 (issue 3) : pp 326-37

Dates: Created 2009/05/19; Completed 2009/08/21;

PMID: 19362804, status: MEDLINE (last retrieval date: 8/21/2009, IMS Date: )

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.