How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?
Identifieur interne : 000119 ( Main/Exploration ); précédent : 000118; suivant : 000120How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?
Auteurs : Danesh Tarapore [Royaume-Uni] ; Jeff Clune [États-Unis] ; Antoine Cully [Royaume-Uni] ; Jean-Baptiste Mouret [France]Source :
English descriptors
- mix :
Abstract
The recently introduced Intelligent Trial and Error algorithm (IT&E) both improves the ability to automatically generate controllers that transfer to real robots, and enables robots to creatively adapt to damage in less than 2 minutes. A key component of IT&E is a new evolutionary algorithm called MAP-Elites, which creates a behavior-performance map that is provided as a set of " creative " ideas to an online learning algorithm. To date, all experiments with MAP-Elites have been performed with a directly encoded list of parameters: it is therefore unknown how MAP-Elites would behave with more advanced encodings, like HyperNeat and SUPG. In addition, because we ultimately want robots that respond to their environments via sensors, we investigate the ability of MAP-Elites to evolve closed-loop controllers, which are more complicated, but also more powerful. Our results show that the encoding critically impacts the quality of the results of MAP-Elites, and that the differences are likely linked to the locality of the encoding (the likelihood of generating a similar behavior after a single mutation). Overall, these results improve our understanding of both the dynamics of the MAP-Elites algorithm and how to best harness MAP-Elites to evolve effective and adaptable robotic controllers.
Url:
DOI: 10.1145/2908812.2908875
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Hal, to step Corpus: 002817
- to stream Hal, to step Curation: 002817
- to stream Hal, to step Checkpoint: 000128
- to stream Main, to step Merge: 000109
- to stream Main, to step Curation: 000119
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?</title><author><name sortKey="Tarapore, Danesh" sort="Tarapore, Danesh" uniqKey="Tarapore D" first="Danesh" last="Tarapore">Danesh Tarapore</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-124942" status="VALID"><orgName>University of York [York]</orgName><desc><address><addrLine>Heslington, York, YO10 5DD</addrLine><country key="GB"></country></address><ref type="url">http://www.york.ac.uk/</ref></desc></hal:affiliation><country>Royaume-Uni</country></affiliation></author><author><name sortKey="Clune, Jeff" sort="Clune, Jeff" uniqKey="Clune J" first="Jeff" last="Clune">Jeff Clune</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-303412" status="VALID"><orgName>University of Wyoming</orgName><orgName type="acronym">UW</orgName><desc><address><addrLine>1000 E. University Ave. Laramie, WY 82071</addrLine><country key="US"></country></address><ref type="url">http://www.uwyo.edu/</ref></desc></hal:affiliation><country>États-Unis</country></affiliation></author><author><name sortKey="Cully, Antoine" sort="Cully, Antoine" uniqKey="Cully A" first="Antoine" last="Cully">Antoine Cully</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-69530" status="VALID"><orgName>Imperial College London</orgName><desc><address><addrLine>Imperial College London, South Kensington Campus, London SW7 2AZ</addrLine><country key="GB"></country></address><ref type="url">http://www3.imperial.ac.uk/</ref></desc></hal:affiliation><country>Royaume-Uni</country></affiliation></author><author><name sortKey="Mouret, Jean Baptiste" sort="Mouret, Jean Baptiste" uniqKey="Mouret J" first="Jean-Baptiste" last="Mouret">Jean-Baptiste Mouret</name><affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-415996" status="VALID"><idno type="RNSR">201521241C</idno><orgName>Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment</orgName><orgName type="acronym">LARSEN</orgName><desc><address><country key="FR"></country></address><ref type="url">http://www.inria.fr/equipes/larsen</ref></desc><listRelation><relation active="#struct-129671" type="direct"></relation><relation active="#struct-300009" type="indirect"></relation><relation active="#struct-423090" type="direct"></relation><relation active="#struct-206040" type="indirect"></relation><relation active="#struct-413289" type="indirect"></relation><relation name="UMR7503" active="#struct-441569" type="indirect"></relation></listRelation><tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno><orgName>INRIA Nancy - Grand Est</orgName><desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine><country key="FR"></country></address><ref type="url">http://www.inria.fr/nancy</ref></desc><listRelation><relation active="#struct-300009" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName><orgName type="acronym">Inria</orgName><desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.inria.fr/en/</ref></desc></org></tutelle><tutelle active="#struct-423090" type="direct"><org type="department" xml:id="struct-423090" status="VALID"><orgName>Department of Complex Systems, Artificial Intelligence & Robotics</orgName><orgName type="acronym">LORIA - AIS</orgName><desc><address><country key="FR"></country></address><ref type="url">http://www.loria.fr/la-recherche-en/departements/complex-system-and-artificial-intelligence</ref></desc><listRelation><relation active="#struct-206040" type="direct"></relation><relation active="#struct-300009" type="indirect"></relation><relation active="#struct-413289" type="indirect"></relation><relation name="UMR7503" active="#struct-441569" type="indirect"></relation></listRelation></org></tutelle><tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno><idno type="RNSR">198912571S</idno><idno type="IdUnivLorraine">[UL]RSI--</idno><orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName><orgName type="acronym">LORIA</orgName><date type="start">2012-01-01</date><desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.loria.fr</ref></desc><listRelation><relation active="#struct-300009" type="direct"></relation><relation active="#struct-413289" type="direct"></relation><relation name="UMR7503" active="#struct-441569" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno><idno type="IdUnivLorraine">[UL]100--</idno><orgName>Université de Lorraine</orgName><orgName type="acronym">UL</orgName><date type="start">2012-01-01</date><desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lorraine.fr/</ref></desc></org></tutelle><tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno><idno type="IdRef">02636817X</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Nancy</settlement><settlement type="city">Metz</settlement><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region></placeName><orgName type="university">Université de Lorraine</orgName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">HAL</idno><idno type="RBID">Hal:hal-01302658</idno><idno type="halId">hal-01302658</idno><idno type="halUri">https://hal.inria.fr/hal-01302658</idno><idno type="url">https://hal.inria.fr/hal-01302658</idno><idno type="doi">10.1145/2908812.2908875</idno><date when="2016">2016</date><idno type="wicri:Area/Hal/Corpus">002817</idno><idno type="wicri:Area/Hal/Curation">002817</idno><idno type="wicri:Area/Hal/Checkpoint">000128</idno><idno type="wicri:explorRef" wicri:stream="Hal" wicri:step="Checkpoint">000128</idno><idno type="wicri:Area/Main/Merge">000109</idno><idno type="wicri:Area/Main/Curation">000119</idno><idno type="wicri:Area/Main/Exploration">000119</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?</title><author><name sortKey="Tarapore, Danesh" sort="Tarapore, Danesh" uniqKey="Tarapore D" first="Danesh" last="Tarapore">Danesh Tarapore</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-124942" status="VALID"><orgName>University of York [York]</orgName><desc><address><addrLine>Heslington, York, YO10 5DD</addrLine><country key="GB"></country></address><ref type="url">http://www.york.ac.uk/</ref></desc></hal:affiliation><country>Royaume-Uni</country></affiliation></author><author><name sortKey="Clune, Jeff" sort="Clune, Jeff" uniqKey="Clune J" first="Jeff" last="Clune">Jeff Clune</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-303412" status="VALID"><orgName>University of Wyoming</orgName><orgName type="acronym">UW</orgName><desc><address><addrLine>1000 E. University Ave. Laramie, WY 82071</addrLine><country key="US"></country></address><ref type="url">http://www.uwyo.edu/</ref></desc></hal:affiliation><country>États-Unis</country></affiliation></author><author><name sortKey="Cully, Antoine" sort="Cully, Antoine" uniqKey="Cully A" first="Antoine" last="Cully">Antoine Cully</name><affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-69530" status="VALID"><orgName>Imperial College London</orgName><desc><address><addrLine>Imperial College London, South Kensington Campus, London SW7 2AZ</addrLine><country key="GB"></country></address><ref type="url">http://www3.imperial.ac.uk/</ref></desc></hal:affiliation><country>Royaume-Uni</country></affiliation></author><author><name sortKey="Mouret, Jean Baptiste" sort="Mouret, Jean Baptiste" uniqKey="Mouret J" first="Jean-Baptiste" last="Mouret">Jean-Baptiste Mouret</name><affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-415996" status="VALID"><idno type="RNSR">201521241C</idno><orgName>Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment</orgName><orgName type="acronym">LARSEN</orgName><desc><address><country key="FR"></country></address><ref type="url">http://www.inria.fr/equipes/larsen</ref></desc><listRelation><relation active="#struct-129671" type="direct"></relation><relation active="#struct-300009" type="indirect"></relation><relation active="#struct-423090" type="direct"></relation><relation active="#struct-206040" type="indirect"></relation><relation active="#struct-413289" type="indirect"></relation><relation name="UMR7503" active="#struct-441569" type="indirect"></relation></listRelation><tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno><orgName>INRIA Nancy - Grand Est</orgName><desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine><country key="FR"></country></address><ref type="url">http://www.inria.fr/nancy</ref></desc><listRelation><relation active="#struct-300009" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName><orgName type="acronym">Inria</orgName><desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.inria.fr/en/</ref></desc></org></tutelle><tutelle active="#struct-423090" type="direct"><org type="department" xml:id="struct-423090" status="VALID"><orgName>Department of Complex Systems, Artificial Intelligence & Robotics</orgName><orgName type="acronym">LORIA - AIS</orgName><desc><address><country key="FR"></country></address><ref type="url">http://www.loria.fr/la-recherche-en/departements/complex-system-and-artificial-intelligence</ref></desc><listRelation><relation active="#struct-206040" type="direct"></relation><relation active="#struct-300009" type="indirect"></relation><relation active="#struct-413289" type="indirect"></relation><relation name="UMR7503" active="#struct-441569" type="indirect"></relation></listRelation></org></tutelle><tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno><idno type="RNSR">198912571S</idno><idno type="IdUnivLorraine">[UL]RSI--</idno><orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName><orgName type="acronym">LORIA</orgName><date type="start">2012-01-01</date><desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.loria.fr</ref></desc><listRelation><relation active="#struct-300009" type="direct"></relation><relation active="#struct-413289" type="direct"></relation><relation name="UMR7503" active="#struct-441569" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno><idno type="IdUnivLorraine">[UL]100--</idno><orgName>Université de Lorraine</orgName><orgName type="acronym">UL</orgName><date type="start">2012-01-01</date><desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lorraine.fr/</ref></desc></org></tutelle><tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno><idno type="IdRef">02636817X</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Nancy</settlement><settlement type="city">Metz</settlement><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region></placeName><orgName type="university">Université de Lorraine</orgName></affiliation></author></analytic><idno type="DOI">10.1145/2908812.2908875</idno></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>MAP-Elites</term><term>divergent search</term><term>evolutionary robotics</term><term>intelli-gent trial and error</term><term>neuroevolution</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">The recently introduced Intelligent Trial and Error algorithm (IT&E) both improves the ability to automatically generate controllers that transfer to real robots, and enables robots to creatively adapt to damage in less than 2 minutes. A key component of IT&E is a new evolutionary algorithm called MAP-Elites, which creates a behavior-performance map that is provided as a set of " creative " ideas to an online learning algorithm. To date, all experiments with MAP-Elites have been performed with a directly encoded list of parameters: it is therefore unknown how MAP-Elites would behave with more advanced encodings, like HyperNeat and SUPG. In addition, because we ultimately want robots that respond to their environments via sensors, we investigate the ability of MAP-Elites to evolve closed-loop controllers, which are more complicated, but also more powerful. Our results show that the encoding critically impacts the quality of the results of MAP-Elites, and that the differences are likely linked to the locality of the encoding (the likelihood of generating a similar behavior after a single mutation). Overall, these results improve our understanding of both the dynamics of the MAP-Elites algorithm and how to best harness MAP-Elites to evolve effective and adaptable robotic controllers.</div></front></TEI><affiliations><list><country><li>France</li><li>Royaume-Uni</li><li>États-Unis</li></country><region><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Metz</li><li>Nancy</li></settlement><orgName><li>Université de Lorraine</li></orgName></list><tree><country name="Royaume-Uni"><noRegion><name sortKey="Tarapore, Danesh" sort="Tarapore, Danesh" uniqKey="Tarapore D" first="Danesh" last="Tarapore">Danesh Tarapore</name></noRegion><name sortKey="Cully, Antoine" sort="Cully, Antoine" uniqKey="Cully A" first="Antoine" last="Cully">Antoine Cully</name></country><country name="États-Unis"><noRegion><name sortKey="Clune, Jeff" sort="Clune, Jeff" uniqKey="Clune J" first="Jeff" last="Clune">Jeff Clune</name></noRegion></country><country name="France"><region name="Grand Est"><name sortKey="Mouret, Jean Baptiste" sort="Mouret, Jean Baptiste" uniqKey="Mouret J" first="Jean-Baptiste" last="Mouret">Jean-Baptiste Mouret</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000119 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000119 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= Hal:hal-01302658
|texte= How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?
}}
| This area was generated with Dilib version V0.6.33. |  |