{"id":"https://openalex.org/W4392903533","doi":"https://doi.org/10.1109/icassp48485.2024.10446781","title":"Offline Reinforcement Learning Based on Next State Supervision","display_name":"Offline Reinforcement Learning Based on Next State Supervision","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903533","doi":"https://doi.org/10.1109/icassp48485.2024.10446781"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108143385","display_name":"Jie Yan","orcid":"https://orcid.org/0009-0002-6436-7912"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yan","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Soochow,China","School of Computer Science and Technology, Soochow University, Soochow, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Soochow,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Soochow, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414574","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-8710-1810"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Soochow,China","Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Soochow, China","School of Computer Science and Technology, Soochow University, Soochow, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Soochow,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Soochow, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Soochow, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414901","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0002-5201-4792"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Zhang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Soochow,China","School of Computer Science and Technology, Soochow University, Soochow, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Soochow,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Soochow, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5775","last_page":"5779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9941999912261963,"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":0.9412263631820679},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7878378033638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437505722045898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622192025184631},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5564181804656982},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5171498656272888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4680214822292328},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4667746126651764},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4568539261817932},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42921698093414307},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33941587805747986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13764774799346924},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1291462779045105},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10173577070236206}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9412263631820679},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7878378033638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437505722045898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622192025184631},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5564181804656982},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5171498656272888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4680214822292328},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4667746126651764},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4568539261817932},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42921698093414307},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33941587805747986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13764774799346924},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1291462779045105},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10173577070236206},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1055180593","display_name":null,"funder_award_id":"61772355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2891303054","display_name":null,"funder_award_id":"62176175","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5943078920","display_name":null,"funder_award_id":"62376179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6225290239","display_name":null,"funder_award_id":"61876217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8274064415","display_name":null,"funder_award_id":"61702055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null},{"id":"https://openalex.org/F4320328898","display_name":"Natural Science Foundation of Xinjiang","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2396881363","https://openalex.org/W2736601468","https://openalex.org/W2947150733","https://openalex.org/W2953981431","https://openalex.org/W3016525976","https://openalex.org/W3033324992","https://openalex.org/W3172360140","https://openalex.org/W3198517287","https://openalex.org/W4282813201","https://openalex.org/W4286895564","https://openalex.org/W4287118283","https://openalex.org/W4306818327","https://openalex.org/W4319303175","https://openalex.org/W4382202996","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6764976746","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6801402327","https://openalex.org/W6802659552","https://openalex.org/W6810450869","https://openalex.org/W6810906561","https://openalex.org/W6838356327","https://openalex.org/W6840663452","https://openalex.org/W6846142413","https://openalex.org/W6853012607"],"related_works":["https://openalex.org/W2501594388","https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1,54],"learning":[2,40,55],"aims":[3],"to":[4,12],"maximize":[5],"the":[6,18,21,68,79,82,90,98,101,105,112,115,118],"use":[7],"of":[8,23,64,100,117],"static":[9],"offline":[10,53],"datasets":[11],"train":[13],"agents":[14],"without":[15],"interacting":[16],"with":[17,81,121],"environment.":[19],"For":[20],"problem":[22],"distribution":[24],"shifts,":[25],"most":[26],"approaches":[27],"avoid":[28],"out-of-distribution":[29],"actions":[30],"through":[31],"strong":[32],"constraints,":[33],"and":[34,39,71,93],"do":[35],"not":[36],"consider":[37],"generalization":[38,126],"within":[41,85],"these":[42],"domains.":[43],"Based":[44],"on":[45,57],"this":[46],"problem,":[47],"we":[48],"propose":[49],"a":[50,86],"novel":[51],"method":[52,113,120],"based":[56],"next":[58],"state":[59,92],"supervision":[60],"(NSS),":[61],"which":[62],"consists":[63],"two":[65],"main":[66],"components,":[67],"guidance":[69,76],"policy":[70,77],"an":[72,94],"adaptive":[73,95],"coefficient.":[74],"The":[75],"outputs":[78],"next-state":[80],"highest":[83],"value":[84],"certain":[87],"range":[88],"around":[89],"current":[91],"coefficient":[96],"regulates":[97],"weight":[99],"penalty":[102],"term":[103],"in":[104],"learned":[106],"policy.":[107],"Empirical":[108],"studies":[109],"show":[110],"that":[111],"improves":[114],"performance":[116],"baseline":[119],"constraints":[122],"while":[123],"having":[124],"some":[125],"ability.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}