The University of Southampton
University of Southampton Institutional Repository

Evolvability signatures of generative encodings: Beyond standard performance benchmarks

Evolvability signatures of generative encodings: Beyond standard performance benchmarks
Evolvability signatures of generative encodings: Beyond standard performance benchmarks
Evolutionary robotics is a promising approach to autonomously synthesize machines with abilities that resemble those of animals, but the field suffers from a lack of strong foundations. In particular, evolutionary systems are currently assessed solely by the fitness score their evolved artifacts can achieve for a specific task, whereas such fitness-based comparisons provide limited insights about how the same system would evaluate on different tasks, and its adaptive capabilities to respond to changes in fitness (e.g., from damages to the machine, or in new situations). To counter these limitations, we introduce the concept of “evolvability signatures”, which picture the post-mutation statistical distribution of both behavior diversity (how different are the robot behaviors after a mutation?) and fitness values (how different is the fitness after a mutation?). We tested the relevance of this concept by evolving controllers for hexapod robot locomotion using five different genotype-to-phenotype mappings (direct encoding, generative encoding of open-loop and closed-loop central pattern generators, generative encoding of neural networks, and single-unit pattern generators (SUPG)). We observed a predictive relationship between the evolvability signature of each encoding and the number of generations required by hexapods to adapt from incurred damages. Our study also reveals that, across the five investigated encodings, the SUPG scheme achieved the best evolvability signature, and was always foremost in recovering an effective gait following robot damages. Overall, our evolvability signatures neatly complement existing task-performance benchmarks, and pave the way for stronger foundations for research in evolutionary robotics.
0020-0255
43-61
Tarapore, Danesh
fe8ec8ae-1fad-4726-abef-84b538542ee4
Mouret, Jean-Baptiste
a837dbc0-1852-4e6f-93d8-41d927305eaf
Tarapore, Danesh
fe8ec8ae-1fad-4726-abef-84b538542ee4
Mouret, Jean-Baptiste
a837dbc0-1852-4e6f-93d8-41d927305eaf

Tarapore, Danesh and Mouret, Jean-Baptiste (2015) Evolvability signatures of generative encodings: Beyond standard performance benchmarks. Information Sciences, 313, 43-61. (doi:10.1016/j.ins.2015.03.046).

Record type: Article

Abstract

Evolutionary robotics is a promising approach to autonomously synthesize machines with abilities that resemble those of animals, but the field suffers from a lack of strong foundations. In particular, evolutionary systems are currently assessed solely by the fitness score their evolved artifacts can achieve for a specific task, whereas such fitness-based comparisons provide limited insights about how the same system would evaluate on different tasks, and its adaptive capabilities to respond to changes in fitness (e.g., from damages to the machine, or in new situations). To counter these limitations, we introduce the concept of “evolvability signatures”, which picture the post-mutation statistical distribution of both behavior diversity (how different are the robot behaviors after a mutation?) and fitness values (how different is the fitness after a mutation?). We tested the relevance of this concept by evolving controllers for hexapod robot locomotion using five different genotype-to-phenotype mappings (direct encoding, generative encoding of open-loop and closed-loop central pattern generators, generative encoding of neural networks, and single-unit pattern generators (SUPG)). We observed a predictive relationship between the evolvability signature of each encoding and the number of generations required by hexapods to adapt from incurred damages. Our study also reveals that, across the five investigated encodings, the SUPG scheme achieved the best evolvability signature, and was always foremost in recovering an effective gait following robot damages. Overall, our evolvability signatures neatly complement existing task-performance benchmarks, and pave the way for stronger foundations for research in evolutionary robotics.

Text
1410.4985 - Author's Original
Restricted to Repository staff only
Request a copy

More information

Accepted/In Press date: 22 March 2015
e-pub ahead of print date: 28 March 2015
Published date: 20 August 2015
Organisations: Agents, Interactions & Complexity

Identifiers

Local EPrints ID: 410784
URI: https://eprints.soton.ac.uk/id/eprint/410784
ISSN: 0020-0255
PURE UUID: ef81aa4b-f11d-4629-b6e4-6cb4529a0aef
ORCID for Danesh Tarapore: ORCID iD orcid.org/0000-0002-3226-6861

Catalogue record

Date deposited: 09 Jun 2017 09:38
Last modified: 29 Oct 2019 01:28

Export record

Altmetrics

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×