Miconi, T and Channon, A ORCID: https://orcid.org/0000-0001-9224-4931 (2005) A virtual creatures model for studies in artificial evolution. In: 2005 IEEE Congress on Evolutionary Computation, vols 1-3, proceedings. IEEE, New York, 565 -572.

[img]
Preview
Text
A virtual creatures model for studies in artificial evolution (AChannon).pdf - Accepted Version

Download (294kB) | Preview

Abstract

We present the results of our replication of Karl Sims' work on the evolution of artificial creatures in a physically realistic 3D environment. We used standard McCulloch-Pitts neurons instead of a more complex set of ad hoc neurons, which we believe makes our model a more general tool for future experiments in artificial (co-)evolution. We provide a detailed description of our model and freely accessible source code. We describe our results both qualitatively and quantitatively, including an analysis of some evolved neural controllers. To the. best of our knowledge, our work is the first replication of Sims' efforts to achieve results comparable to Sims' in efficiency and complexity, with standard neurons and realistic Newtonian physics.

Item Type: Book Section
Additional Information: © IEEE. This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/CEC.2005.1554733 - please refer to any applicable terms of use of the publisher.
Uncontrolled Keywords: computer science, artificial intelligence
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Natural Sciences > School of Computing and Maths
Related URLs:
Depositing User: Symplectic
Date Deposited: 11 Nov 2014 10:40
Last Modified: 17 Dec 2018 10:45
URI: http://eprints.keele.ac.uk/id/eprint/35

Actions (login required)

View Item View Item