{"id":"https://openalex.org/W4391454561","doi":"https://doi.org/10.1109/access.2024.3361030","title":"Combined Constraint on Behavior Cloning and Discriminator in Offline Reinforcement Learning","display_name":"Combined Constraint on Behavior Cloning and Discriminator in Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391454561","doi":"https://doi.org/10.1109/access.2024.3361030"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3361030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361030","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418100.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418100.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093843558","display_name":"Shunya Kidera","orcid":"https://orcid.org/0009-0009-7049-5882"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shunya Kidera","raw_affiliation_strings":["Electrical Engineering Department, Kanazawa University, Kanazawa, Japan"],"raw_orcid":"https://orcid.org/0009-0009-7049-5882","affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032746049","display_name":"Kosuke Shintani","orcid":"https://orcid.org/0000-0003-0581-5658"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kosuke Shintani","raw_affiliation_strings":["Electrical Engineering Department, Kanazawa University, Kanazawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000097788","display_name":"Toi Tsuneda","orcid":"https://orcid.org/0000-0003-1913-9179"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toi Tsuneda","raw_affiliation_strings":["Electrical Engineering Department, Kanazawa University, Kanazawa, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1913-9179","affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102728648","display_name":"Satoshi Yamane","orcid":"https://orcid.org/0000-0001-7883-4054"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Yamane","raw_affiliation_strings":["Electrical Engineering Department, Kanazawa University, Kanazawa, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7883-4054","affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093843558"],"corresponding_institution_ids":["https://openalex.org/I10091056"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3016,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8197448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"19942","last_page":"19951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.770799994468689,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.770799994468689,"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/discriminator","display_name":"Discriminator","score":0.8204883933067322},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7797343730926514},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.6567035913467407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6421977877616882},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5635961294174194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485332012176514},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44135603308677673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3431035280227661},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1805516481399536},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08812198042869568},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08572587370872498},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06112602353096008}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8204883933067322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7797343730926514},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.6567035913467407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6421977877616882},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5635961294174194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485332012176514},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44135603308677673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3431035280227661},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1805516481399536},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08812198042869568},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08572587370872498},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06112602353096008},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1109/access.2024.3361030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361030","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418100.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:76a2d0b3cd5f4e4db06a44e5c86f7273","is_oa":true,"landing_page_url":"https://doaj.org/article/76a2d0b3cd5f4e4db06a44e5c86f7273","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 19942-19951 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3361030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361030","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418100.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2186355850","display_name":null,"funder_award_id":"BS123456","funder_id":"https://openalex.org/F4320306111","funder_display_name":"U.S. Department of Commerce"}],"funders":[{"id":"https://openalex.org/F4320306111","display_name":"U.S. Department of Commerce","ror":"https://ror.org/04chq2495"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391454561.pdf","grobid_xml":"https://content.openalex.org/works/W4391454561.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1986014385","https://openalex.org/W2024390895","https://openalex.org/W2031571562","https://openalex.org/W2112420033","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2566467060","https://openalex.org/W2810785043","https://openalex.org/W2953981431","https://openalex.org/W2990138404","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3036619998","https://openalex.org/W3041202696","https://openalex.org/W3172360140","https://openalex.org/W4214717370","https://openalex.org/W4360584316","https://openalex.org/W6631190155","https://openalex.org/W6640174482","https://openalex.org/W6680724558","https://openalex.org/W6718092244","https://openalex.org/W6731259203","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6753243525","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6764976746","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6780559895","https://openalex.org/W6796589144"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2057775761","https://openalex.org/W2985313479"],"abstract_inverted_index":{"In":[0,40,105,150],"recent":[1,41],"years,":[2,42],"reinforcement":[3],"learning":[4,197],"(RL)":[5],"has":[6,44],"received":[7],"a":[8,46,88,110,143,161],"lot":[9,47],"of":[10,48,87,167],"attention":[11],"because":[12,86],"we":[13,108],"can":[14],"automatically":[15],"learn":[16,36],"optimal":[17],"behavioral":[18],"policies.":[19],"However,":[20],"since":[21],"RL":[22,52,80,85,113,128],"acquires":[23],"the":[24,30,62,67,126,136,152,165,168,204,218],"policy":[25],"by":[26,77,184],"repeatedly":[27],"interacting":[28],"with":[29,61,139],"environment,":[31,63],"it":[32],"is":[33,199],"difficult":[34],"to":[35,59,83,94,125,156,173,187,195,211],"about":[37],"realistic":[38],"tasks.":[39],"there":[43],"been":[45,99],"research":[49],"on":[50,203],"offline":[51,84,103,112,127],"(batch":[53],"RL),":[54],"which":[55],"does":[56,74],"not":[57,75,200],"need":[58],"interact":[60],"but":[64,160],"learns":[65],"from":[66,118],"accumulated":[68],"experience":[69],"prepared":[70],"in":[71,102,121,175,215],"advance.":[72],"Learning":[73],"work":[76],"applying":[78],"common":[79],"methods":[81,141],"directly":[82],"problem":[89],"called":[90,130],"distributional":[91,96],"shift.":[92],"Methods":[93],"suppress":[95,157],"shift":[97,190],"have":[98],"actively":[100],"studied":[101],"RL.":[104],"this":[106,182],"study,":[107],"propose":[109],"new":[111,193],"algorithm":[114],"that":[115,198],"adds":[116],"constraints":[117,194],"discriminators":[119],"used":[120],"Generative":[122],"Adversarial":[123],"Networks":[124],"method":[129,138],"TD3+BC.":[131],"We":[132],"compare":[133],"and":[134],"validate":[135],"proposed":[137,179],"existing":[140],"using":[142],"benchmark":[144],"for":[145],"3D":[146],"robot":[147],"control":[148],"simulation.":[149],"TD3+BC,":[151],"constraint":[153],"was":[154,170],"tightened":[155],"distribution":[158,189],"shift,":[159],"challenge":[162],"arose":[163],"when":[164],"quality":[166],"dataset":[169,219],"poor,":[171],"leading":[172],"difficulties":[174],"successful":[176],"learning.":[177],"The":[178],"approach":[180],"addresses":[181],"issue":[183],"incorporating":[185],"features":[186],"mitigate":[188],"while":[191],"introducing":[192],"enable":[196],"solely":[201],"dependent":[202],"dataset\u2019s":[205],"quality.":[206],"This":[207],"innovative":[208],"strategy":[209],"aims":[210],"improve":[212],"accuracy":[213],"even":[214],"cases":[216],"where":[217],"exhibits":[220],"poor":[221],"characteristics.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}