{"id":"https://openalex.org/W4400412158","doi":"https://doi.org/10.1145/3638529.3654045","title":"Multi-Objective Evolutionary Hindsight Experience Replay for Robot Manipulation Tasks","display_name":"Multi-Objective Evolutionary Hindsight Experience Replay for Robot Manipulation Tasks","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4400412158","doi":"https://doi.org/10.1145/3638529.3654045"},"language":"en","primary_location":{"id":"doi:10.1145/3638529.3654045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638529.3654045","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022288387","display_name":"Erdi Sayar","orcid":"https://orcid.org/0000-0002-5944-7291"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erdi Sayar","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5944-7291","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007121933","display_name":"Giovanni Iacca","orcid":"https://orcid.org/0000-0001-9723-1830"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Iacca","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9723-1830","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4840-076X","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9991000294685364,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/hindsight-bias","display_name":"Hindsight bias","score":0.8946847915649414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6943281888961792},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6768149137496948},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4877079427242279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4653609097003937},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.15895026922225952},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13557785749435425}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.8946847915649414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6943281888961792},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6768149137496948},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4877079427242279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4653609097003937},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.15895026922225952},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13557785749435425}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3638529.3654045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638529.3654045","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/418990","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/3638529.3654045","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1499692130","https://openalex.org/W1949804828","https://openalex.org/W2040622444","https://openalex.org/W2061504687","https://openalex.org/W2109042184","https://openalex.org/W2126105956","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2593658277","https://openalex.org/W2612690371","https://openalex.org/W2962687375","https://openalex.org/W2999905431","https://openalex.org/W3165718346","https://openalex.org/W4250503569","https://openalex.org/W4287167165","https://openalex.org/W4287757595"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3089780453"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9],"(RL)":[2],"algorithms":[3],"often":[4],"face":[5],"challenges":[6],"in":[7,28],"efficiently":[8],"effective":[10],"policies":[11],"for":[12],"sparse-reward":[13,165],"multi-goal":[14],"robot":[15,166],"manipulation":[16,167],"tasks,":[17,168],"thus":[18],"requiring":[19],"a":[20,77,91,104,115,134],"vast":[21],"amount":[22],"of":[23,79],"experiences.":[24],"The":[25,180],"state-of-the-art":[26],"algorithm":[27,119],"the":[29,44,55,61,143,145,157,194],"field,":[30],"Hindsight":[31,68,111],"Experience":[32,112],"Replay":[33,113],"(HER),":[34],"addresses":[35],"this":[36,66],"issue":[37],"by":[38,107],"using":[39],"failed":[40],"trajectories":[41],"and":[42,94,127,148,170,173,178],"replacing":[43],"desired":[45,56],"goal":[46,57],"with":[47,169,176,190],"hindsight":[48],"goals.":[49],"However,":[50],"HER":[51,177],"performs":[52,187],"poorly":[53],"when":[54],"is":[58,88,137],"distant":[59],"from":[60,81],"initial":[62],"state.":[63],"To":[64],"address":[65],"limitation,":[67],"Goal":[69],"Generation":[70],"(HGG)":[71],"has":[72],"been":[73],"proposed,":[74],"which":[75],"generates":[76],"curriculum":[78,86,117,122,135],"goals":[80],"already":[82],"visited":[83],"states.":[84],"This":[85],"generation":[87,123],"based":[89],"on":[90,156,162,188,193],"single":[92],"objective,":[93],"does":[95],"not":[96],"take":[97],"obstacles":[98],"into":[99],"account.":[100],"Here,":[101],"we":[102],"make":[103],"step":[105],"forward":[106],"proposing":[108],"Multi-Objective":[109],"Evolutionary":[110],"(MOEHER),":[114],"novel":[116],"RL":[118],"that":[120,136,183],"reformulates":[121],"considering":[124],"multiple":[125],"objectives":[126],"obstacles.":[128,158],"MOEHER":[129,161,184],"utilizes":[130],"NSGA-II":[131],"to":[132],"generate":[133],"optimized":[138],"w.r.t.":[139],"four":[140,163],"objectives,":[141],"namely":[142],"Q-function,":[144],"goal-proximity":[146],"function,":[147],"two":[149],"distance":[150],"metrics,":[151],"while":[152],"simultaneously":[153],"satisfying":[154],"constraints":[155],"We":[159],"evaluate":[160],"different":[164],"without":[171],"obstacles,":[172],"compare":[174],"it":[175],"HGG.":[179],"results":[181],"demonstrate":[182],"surpasses":[185],"or":[186],"par":[189],"these":[191],"methods":[192],"tested":[195],"tasks.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-07-09T00:00:00"}