{"id":"https://openalex.org/W4389665552","doi":"https://doi.org/10.1109/iros55552.2023.10342236","title":"Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness","display_name":"Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665552","doi":"https://doi.org/10.1109/iros55552.2023.10342236"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5053814168","display_name":"Wendyam Eric Lionel Ilboudo","orcid":"https://orcid.org/0000-0002-1518-2519"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wendyam Eric Lionel Ilboudo","raw_affiliation_strings":["Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041015496","display_name":"Taisuke Kobayashi","orcid":"https://orcid.org/0000-0002-7368-8614"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taisuke Kobayashi","raw_affiliation_strings":["National Institute of Informatics/The Graduate University for Advanced Studies, SOKENDAI,Tokyo,Japan","National Institute of Informatics/The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics/The Graduate University for Advanced Studies, SOKENDAI,Tokyo,Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics/The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Division of Information Science,Nara,Japan,630-0192","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58617936,"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":"5622","last_page":"5629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9562000036239624,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8486194610595703},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7273983359336853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993297934532166},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5849353671073914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5317928194999695},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4457119107246399},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4311329424381256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1581258475780487}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8486194610595703},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7273983359336853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993297934532166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5849353671073914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317928194999695},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4457119107246399},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4311329424381256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1581258475780487},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W2105078254","https://openalex.org/W2158782408","https://openalex.org/W2530195778","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2904246096","https://openalex.org/W2913602408","https://openalex.org/W2914994663","https://openalex.org/W2916286980","https://openalex.org/W2945586853","https://openalex.org/W2950300520","https://openalex.org/W2963390419","https://openalex.org/W2963614114","https://openalex.org/W2963906246","https://openalex.org/W2968116426","https://openalex.org/W2969489701","https://openalex.org/W3003774673","https://openalex.org/W3035389468","https://openalex.org/W3092609815","https://openalex.org/W3118300017","https://openalex.org/W3126300335","https://openalex.org/W3173329083","https://openalex.org/W3202021423","https://openalex.org/W3203489455","https://openalex.org/W4246659208","https://openalex.org/W4246840991","https://openalex.org/W6616173779","https://openalex.org/W6697388432","https://openalex.org/W6728073343","https://openalex.org/W6735677848","https://openalex.org/W6754554871","https://openalex.org/W6757358677","https://openalex.org/W6757592117","https://openalex.org/W6759312646","https://openalex.org/W6759360826","https://openalex.org/W6761443123","https://openalex.org/W6762548700","https://openalex.org/W6764339904","https://openalex.org/W6766952794","https://openalex.org/W6767997047","https://openalex.org/W6779605632","https://openalex.org/W6801655106","https://openalex.org/W6801956738","https://openalex.org/W6802227391"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Domain":[0],"randomization":[1],"(DR)":[2],"is":[3,59],"a":[4,124,137,155,210],"powerful":[5],"framework":[6,190],"that":[7,47,85,157],"has":[8,32],"allowed":[9],"the":[10,30,53,62,64,109,140,146,163,178,215],"transfer":[11],"of":[12,108,162,180,217],"policies":[13,46,79],"from":[14,145],"randomized":[15,65],"domain":[16,39,66,82,93,111],"(a.k.a.":[17],"simulation)":[18],"to":[19,24,33,43,76,91,135,150],"real":[20,55,211],"robots":[21],"with":[22,81,96,184],"little":[23],"no":[25,185],"retraining":[26,186],"requirement.":[27,187],"However,":[28,102],"because":[29],"policy":[31],"perform":[34],"well":[35],"for":[36,221],"many":[37],"different":[38,160],"conditions,":[40],"DR":[41,122,196],"tends":[42],"produce":[44],"sub-optimal":[45],"can":[48,87,112,167],"be":[49,113],"too":[50],"conservative":[51],"on":[52,173,204,209],"target":[54,110],"system.":[56],"This":[57,188],"problem":[58],"further":[60],"exacerbated":[61],"larger":[63],"is.":[67],"To":[68],"tackle":[69],"this":[70,116],"issue,":[71],"recent":[72],"works":[73,194],"have":[74],"proposed":[75],"learn":[77,136],"universal":[78],"(UP)":[80],"knowledge":[83],"such":[84],"they":[86],"adapt":[88,169],"their":[89],"behavior":[90,171],"each":[92],"when":[94],"paired":[95],"an":[97,174],"online":[98],"system":[99,182],"identifier":[100],"(OSI).":[101],"in":[103,195],"most":[104],"applications,":[105],"perfect":[106],"identifications":[107],"impossible.":[114],"In":[115],"paper,":[117],"by":[118],"drawing":[119],"similarities":[120],"between":[121],"as":[123],"multi-domain":[125],"reinforcement":[126,130,199],"learning":[127,131],"and":[128,166,197,207],"multi-objective":[129],"(MORL),":[132],"we":[133],"propose":[134],"UP":[138,156,220],"over":[139],"convex":[141],"coverage":[142],"set":[143,165],"borrowed":[144],"MORL":[147],"theory.":[148],"Thanks":[149],"this,":[151],"our":[152,218],"method":[153],"learns":[154],"effectively":[158],"captures":[159],"sub-domains":[161],"uncertainty":[164],"therefore":[168],"its":[170],"based":[172],"OSI":[175],"uncertainty,":[176],"unlocking":[177],"power":[179],"stochastic":[181],"identification":[183],"pseudo-MORL":[189],"also":[191],"contains":[192],"previous":[193],"robust":[198],"learning.":[200],"We":[201],"conduct":[202],"simulations":[203],"Mujoco":[205],"tasks":[206],"experiments":[208],"D'Claw":[212],"robot,":[213],"revealing":[214],"effectiveness":[216],"domain-uncertainty-aware":[219],"sim-to-real":[222],"transfer.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}