A new evolutionary approach to developing neural autonomous agents

Jinn-Moon Yang, Jorng Tzong Horng, Cheng Yan Kao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This paper explores the use of neural networks to control robots in tasks requiring sequential and learning behavior. We propose a family competition evolutionary algorithm (FCEA) to evolve networks that can integrate these different types of behavior in a smooth and continuous manner. The approach integrates self-Adaptive Gaussian mutation, self-Adaptive Cauchy mutation, decreasing-based Gaussian mutation, and family competition. In order to illustrate the power of the approach, we apply this approach to two different task domains: The artificial ant problem and a sequential behavior problem-an agent learns to play football. From the experimental results, we find our approach performs much better than other evolutionary algorithms in these two tasks. Based on the results from our experiments, it is shown that our approach can evolve neural networks to provide a means of integrating, sequencing and learning within a single control system.

Original languageEnglish
Title of host publicationProceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1411-1416
Number of pages6
ISBN (Print)078034300X
DOIs
StatePublished - 1 Jan 1998
Event15th IEEE International Conference on Robotics and Automation, ICRA 1998 - Leuven, Belgium
Duration: 16 May 199820 May 1998

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Volume2
ISSN (Print)1050-4729

Conference

Conference15th IEEE International Conference on Robotics and Automation, ICRA 1998
CountryBelgium
CityLeuven
Period16/05/9820/05/98

Fingerprint Dive into the research topics of 'A new evolutionary approach to developing neural autonomous agents'. Together they form a unique fingerprint.

Cite this