{"id":"https://openalex.org/W4367000260","doi":"https://doi.org/10.1145/3583133.3590625","title":"Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning","display_name":"Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning","publication_year":2023,"publication_date":"2023-07-15","ids":{"openalex":"https://openalex.org/W4367000260","doi":"https://doi.org/10.1145/3583133.3590625"},"language":"en","primary_location":{"id":"doi:10.1145/3583133.3590625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583133.3590625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.12080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101825660","display_name":"Sim\u00f3n C. Smith","orcid":"https://orcid.org/0000-0001-5453-9659"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sim\u00f3n C. Smith","raw_affiliation_strings":["Imperial College, London, United Kingdom","School of Computing, Engineering and The Built Environment, Edinburgh Napier University, Edinburgh, Midlothian, United Kingdom","Imperial College, London, United Kingdom School of Computing, Engineering and The Built Environment, Edinburgh Napier University, Edinburgh, Midlothian, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"School of Computing, Engineering and The Built Environment, Edinburgh Napier University, Edinburgh, Midlothian, United Kingdom","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"Imperial College, London, United Kingdom School of Computing, Engineering and The Built Environment, Edinburgh Napier University, Edinburgh, Midlothian, United Kingdom","institution_ids":["https://openalex.org/I251738","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011437628","display_name":"Bryan Lim","orcid":"https://orcid.org/0000-0002-2324-1400"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bryan Lim","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027494765","display_name":"Hannah Janmohamed","orcid":"https://orcid.org/0000-0001-7997-8455"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hannah Janmohamed","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011747084","display_name":"Antoine Cully","orcid":"https://orcid.org/0000-0002-3190-7073"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antoine Cully","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101825660"],"corresponding_institution_ids":["https://openalex.org/I251738","https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.1728,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53131531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.8199294209480286},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.7397254705429077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936730146408081},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6379993557929993},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6163604855537415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5481514930725098},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5166113972663879},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.46083930134773254},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4178692102432251},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.35299575328826904},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3041086792945862},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11727243661880493}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.8199294209480286},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.7397254705429077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936730146408081},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6379993557929993},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6163604855537415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481514930725098},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5166113972663879},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.46083930134773254},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4178692102432251},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35299575328826904},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3041086792945862},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11727243661880493},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3583133.3590625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583133.3590625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.12080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12080","pdf_url":"https://arxiv.org/pdf/2304.12080","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.12080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12080","pdf_url":"https://arxiv.org/pdf/2304.12080","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G866405208","display_name":"REcoVER: Learning algorithms for REsilient and VErsatile Robots","funder_award_id":"EP/V006673/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8782551874","display_name":null,"funder_award_id":"EP/V006673/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367000260.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W758372786","https://openalex.org/W2797210984","https://openalex.org/W2962687375","https://openalex.org/W3103202942","https://openalex.org/W3167445240","https://openalex.org/W3200285024","https://openalex.org/W4223426965","https://openalex.org/W4223530229","https://openalex.org/W4283721947"],"related_works":["https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W96259911","https://openalex.org/W2168225754","https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2724299411","https://openalex.org/W4365788246","https://openalex.org/W2913184176","https://openalex.org/W1936970628"],"abstract_inverted_index":{"Learning":[0],"algorithms,":[1],"like":[2],"Quality-Diversity":[3],"(QD),":[4],"can":[5],"be":[6],"used":[7],"to":[8,24,53,76,109,133,161],"acquire":[9],"repertoires":[10],"of":[11,28,118,137],"diverse":[12],"robotics":[13],"skills.":[14],"This":[15,61],"learning":[16],"is":[17],"commonly":[18],"done":[19],"via":[20],"computer":[21],"simulation":[22,41],"due":[23],"the":[25,48,71,74,78,97,107,148,162],"large":[26],"number":[27],"evaluations":[29],"required.":[30],"However,":[31],"training":[32,177],"in":[33,139],"a":[34,38,58,64,102,110,129,135,152,171,179],"virtual":[35],"environment":[36],"generates":[37],"gap":[39],"between":[40,70],"and":[42,73,81,170],"reality.":[43],"Here,":[44],"we":[45,157],"build":[46],"upon":[47],"Reset-Free":[49],"QD":[50],"(RF-QD)":[51],"algorithm":[52],"learn":[54,134],"controllers":[55],"directly":[56],"on":[57,178],"physical":[59,130,180],"robot.":[60],"method":[62,127],"uses":[63],"dynamics":[65,168],"model,":[66],"learned":[67],"from":[68],"interactions":[69],"robot":[72,108,132,181],"environment,":[75],"predict":[77],"robot's":[79],"behaviour":[80,86],"improve":[82],"sample":[83],"efficiency.":[84],"A":[85],"selection":[87],"policy":[88,104,173],"filters":[89],"out":[90],"uninteresting":[91],"or":[92],"unsafe":[93],"policies":[94],"predicted":[95],"by":[96],"model.":[98],"RF-QD":[99],"also":[100],"includes":[101],"recovery":[103,172],"that":[105,125,167],"returns":[106],"safe":[111],"zone":[112],"when":[113],"it":[114],"has":[115],"walked":[116],"outside":[117],"it,":[119],"allowing":[120],"continuous":[121],"learning.":[122],"We":[123,145,165],"demonstrate":[124],"our":[126,159],"enables":[128],"quadruped":[131],"repertoire":[136,150],"behaviours":[138],"two":[140],"hours":[141],"without":[142],"human":[143],"supervision.":[144],"successfully":[146],"test":[147],"solution":[149],"using":[151],"maze":[153],"navigation":[154],"task.":[155],"Finally,":[156],"compare":[158],"approach":[160],"MAP-Elites":[163],"algorithm.":[164],"show":[166],"awareness":[169],"are":[174],"required":[175],"for":[176,182],"optimal":[183],"archive":[184],"generation.":[185],"Video":[186],"available":[187],"at":[188],"https://youtu.be/BgGNvIsRh7Q":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}