{"id":"https://openalex.org/W2962258836","doi":"https://doi.org/10.1145/3319619.3322044","title":"Towards continual reinforcement learning through evolutionary meta-learning","display_name":"Towards continual reinforcement learning through evolutionary meta-learning","publication_year":2019,"publication_date":"2019-07-10","ids":{"openalex":"https://openalex.org/W2962258836","doi":"https://doi.org/10.1145/3319619.3322044","mag":"2962258836"},"language":"en","primary_location":{"id":"doi:10.1145/3319619.3322044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319619.3322044","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.itu.dk/portal/da/publications/c6212d40-15e2-4332-b91f-3567cc5350ca","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089907783","display_name":"Djordje Grbic","orcid":"https://orcid.org/0000-0002-4388-2539"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Djordje Grbic","raw_affiliation_strings":["IT University Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University Copenhagen","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020511097","display_name":"Sebastian Risi","orcid":"https://orcid.org/0000-0003-3607-8400"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sebastian Risi","raw_affiliation_strings":["IT University Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University Copenhagen","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976000189781189,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7661111354827881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5867776870727539},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5049880146980286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4073714017868042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20814481377601624},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06408914923667908}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7661111354827881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867776870727539},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5049880146980286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4073714017868042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20814481377601624},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06408914923667908},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3319619.3322044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319619.3322044","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/c6212d40-15e2-4332-b91f-3567cc5350ca","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/c6212d40-15e2-4332-b91f-3567cc5350ca","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grbic, D & Risi, S 2019, Towards Continual Reinforcement Learning through Evolutionary Meta-Learning. in Towards Continual Reinforcement Learning through Evolutionary Meta-Learning. 2019 edn, vol. Proceedings of the Genetic and Evolutionary Computation Conference Companion, Association for Computing Machinery, New York, NY, USA, pp. 119-120. https://doi.org/10.1145/3319619.3322044","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/c6212d40-15e2-4332-b91f-3567cc5350ca","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/c6212d40-15e2-4332-b91f-3567cc5350ca","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grbic, D & Risi, S 2019, Towards Continual Reinforcement Learning through Evolutionary Meta-Learning. in Towards Continual Reinforcement Learning through Evolutionary Meta-Learning. 2019 edn, vol. Proceedings of the Genetic and Evolutionary Computation Conference Companion, Association for Computing Machinery, New York, NY, USA, pp. 119-120. https://doi.org/10.1145/3319619.3322044","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2089217417","https://openalex.org/W2604763608","https://openalex.org/W2963305465","https://openalex.org/W2964043796"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"In":[0],"continual":[1,41,68],"learning,":[2],"an":[3,167],"agent":[4,50,89],"is":[5,115],"exposed":[6],"to":[7,13,51,90,97,136],"a":[8,58,71,103,108,130],"changing":[9],"environment,":[10],"requiring":[11,87],"it":[12],"adapt":[14,52],"during":[15,53,57,118],"execution":[16,54,119],"time.":[17,120],"While":[18],"traditional":[19],"reinforcement":[20,112,139,145],"learning":[21,69,113,140,146,157],"(RL)":[22],"methods":[23],"have":[24],"shown":[25],"impressive":[26],"results":[27,123],"in":[28,36,70,76],"various":[29],"domains,":[30],"there":[31],"has":[32],"been":[33],"less":[34],"progress":[35],"addressing":[37],"the":[38,49,65,78,81,88,99,126],"challenge":[39],"of":[40,67,80,102,110,144],"learning.":[42],"Current":[43],"RL":[44],"approaches":[45],"do":[46],"not":[47],"allow":[48],"but":[55],"only":[56],"dedicated":[59],"training":[60],"phase.":[61],"Here":[62],"we":[63],"study":[64],"problem":[66],"2D":[72],"bipedal":[73],"walker":[74,82],"domain,":[75],"which":[77],"legs":[79],"grow":[83],"over":[84],"its":[85],"lifetime,":[86],"adapt.":[91],"The":[92,121,142],"introduced":[93],"approach":[94,128],"combines":[95],"neuroevolution,":[96],"determine":[98],"starting":[100],"weights":[101],"deep":[104,111],"neural":[105],"network,":[106],"and":[107,147],"version":[109],"that":[114,125,159],"continually":[116,156],"running":[117],"proof-of-concept":[122],"show":[124],"combined":[127],"gives":[129],"better":[131],"generalisation":[132],"performance":[133],"when":[134],"compared":[135],"evolution":[137,148],"or":[138],"alone.":[141],"hybridization":[143],"opens":[149],"up":[150],"exciting":[151],"new":[152],"research":[153],"directions":[154],"for":[155],"agents":[158],"can":[160],"benefit":[161],"from":[162],"suitable":[163],"priors":[164],"determined":[165],"by":[166],"evolutionary":[168],"process.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
