Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm

Steyven, Andreas; Hart, Emma; Paechter, Ben

Abstract

It is well known that in open-ended evolution, the nature of the environment plays in key role in directing evolution. However, in Evolutionary Robotics, it is often unclear exactly how parameterisation of a given environment might influence the emergence of particular behaviours. We consider environments in which the total amount of energy is parameterised by availability and value, and use surface plots to explore the relationship between those environment parameters and emergent behaviour using a variant of a well-known distributed evolutionary algorithm (mEDEA). Analysis of the resulting landscape show that it is crucial for a researcher to select appropriate parameterisations in order that the environment provides the right balance between facilitating survival and exerting sufficient pressure for new behaviours to emerge. To the best of our knowledge, this is the first time such an analysis has been undertaken.

Citation

Steyven, A., Hart, E., & Paechter, B. (2016, October). Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm. Presented at PPSN 2016 14th International Conference on Parallel Problem Solving from Nature

• Presentation Conference Type: Conference Paper (published)
• Conference Name: PPSN 2016 14th International Conference on Parallel Problem Solving from Nature
• Start Date: Oct 17, 2016
• End Date: Oct 21, 2016
• Acceptance Date: May 30, 2016
• Online Publication Date: Aug 31, 2016
• Publication Date: 2016
• Deposit Date: Jun 1, 2016
• Publicly Available Date: Oct 3, 2016
• Electronic ISSN: 1611-3349
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 921-931
• Series Title: Lecture Notes in Computer Science
• Series Number: 9921
• Series ISSN: 0302-9743
• Book Title: Parallel Problem Solving from Nature – PPSN XIV; Lecture Notes in Computer Science
• ISBN: 9783319458229
• DOI: https://doi.org/10.1007/978-3-319-45823-6_86
• Keywords: Evolutionary algorithm; evolutionary robotics; energy zones
• Public URL: http://researchrepository.napier.ac.uk/id/eprint/10331
• Contract Date: Oct 3, 2016