{"id":"https://openalex.org/W4388469888","doi":"https://doi.org/10.1109/tnnls.2023.3293508","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning With Expert Guidance","display_name":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning With Expert Guidance","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388469888","doi":"https://doi.org/10.1109/tnnls.2023.3293508","pmid":"https://pubmed.ncbi.nlm.nih.gov/37934636"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3293508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3293508","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5045184497","display_name":"Qisen Yang","orcid":"https://orcid.org/0000-0002-2587-2660"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisen Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2587-2660","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015366673","display_name":"Shenzhi Wang","orcid":"https://orcid.org/0009-0000-0314-4243"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenzhi Wang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0314-4243","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103192559","display_name":"Q. Zhang","orcid":"https://orcid.org/0009-0001-7094-4694"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7094-4694","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101868179","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0003-0858-1770"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0858-1770","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.4403,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85226734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"11","first_page":"16288","last_page":"16300"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9613999724388123,"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":0.7235021591186523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5543851852416992},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5072416663169861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39353954792022705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3538596034049988},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18369516730308533}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7235021591186523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543851852416992},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5072416663169861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39353954792022705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538596034049988},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18369516730308533},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3293508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3293508","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37934636","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37934636","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3549978537","display_name":null,"funder_award_id":"2019YFC1408703","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G7410564107","display_name":null,"funder_award_id":"62276150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8753403390","display_name":null,"funder_award_id":"62022048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8973868443","display_name":null,"funder_award_id":"2019YFC1408703","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F3230804744","display_name":"Guoqiang Institute, Tsinghua University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1513013675","https://openalex.org/W1988790447","https://openalex.org/W1989684337","https://openalex.org/W2158782408","https://openalex.org/W2187089797","https://openalex.org/W2201912979","https://openalex.org/W2583993537","https://openalex.org/W2788862220","https://openalex.org/W2884561390","https://openalex.org/W2947150733","https://openalex.org/W2962736495","https://openalex.org/W2962793652","https://openalex.org/W2962894046","https://openalex.org/W2963099939","https://openalex.org/W2963411833","https://openalex.org/W2963561234","https://openalex.org/W2963802910","https://openalex.org/W2964105864","https://openalex.org/W2968983352","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W2997876358","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3100944043","https://openalex.org/W3173345775","https://openalex.org/W3213722353","https://openalex.org/W4226257065","https://openalex.org/W4235681568","https://openalex.org/W4287998029","https://openalex.org/W4297964528","https://openalex.org/W4301178047","https://openalex.org/W4360584316","https://openalex.org/W6631190155","https://openalex.org/W6678925830","https://openalex.org/W6679390333","https://openalex.org/W6681968150","https://openalex.org/W6736057607","https://openalex.org/W6736942654","https://openalex.org/W6737133519","https://openalex.org/W6743661861","https://openalex.org/W6746030470","https://openalex.org/W6746061758","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6750523955","https://openalex.org/W6753772092","https://openalex.org/W6754756046","https://openalex.org/W6755015941","https://openalex.org/W6757469721","https://openalex.org/W6760439459","https://openalex.org/W6763430915","https://openalex.org/W6763704811","https://openalex.org/W6766978945","https://openalex.org/W6769342953","https://openalex.org/W6770887232","https://openalex.org/W6771270455","https://openalex.org/W6771428195","https://openalex.org/W6772111244","https://openalex.org/W6774967489","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6780559895","https://openalex.org/W6783671239","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6810466897","https://openalex.org/W6811554491"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"optimizes":[4],"the":[5,16,22,61,68,118,122,135],"policy":[6,37,41,85,123,126],"on":[7,39,89,147,157],"a":[8,30,36,40,49,55,64,92,105,111],"previously":[9],"collected":[10],"dataset":[11],"without":[12],"any":[13],"interactions":[14],"with":[15,83,109,162],"environment,":[17],"yet":[18],"usually":[19],"suffers":[20],"from":[21],"distributional":[23],"shift":[24],"problem.":[25],"To":[26],"mitigate":[27],"this":[28,73,90],"issue,":[29],"typical":[31],"solution":[32],"is":[33,101,141],"to":[34,115],"impose":[35],"constraint":[38,86,127],"improvement":[42,124],"objective.":[43],"However,":[44],"existing":[45],"methods":[46],"generally":[47],"adopt":[48],"\"one-size-fits-all\"":[50],"practice,":[51],"i.e.,":[52],"keeping":[53],"only":[54,110],"single":[56],"improvement-constraint":[57],"balance":[58],"for":[59,128],"all":[60],"samples":[62,79],"in":[63],"mini-batch":[65],"or":[66],"even":[67],"entire":[69],"offline":[70,98,159],"dataset.":[71],"In":[72],"work,":[74],"we":[75],"argue":[76],"that":[77,134,151],"different":[78,84],"should":[80],"be":[81,154],"treated":[82],"intensities.":[87],"Based":[88],"idea,":[91],"novel":[93],"plug-in":[94],"approach":[95],"named":[96],"guided":[97],"RL":[99,160],"(GORL)":[100],"proposed.":[102],"GORL":[103,152],"employs":[104],"guiding":[106],"network,":[107],"along":[108],"few":[112],"expert":[113],"demonstrations,":[114],"adaptively":[116],"determine":[117],"relative":[119],"importance":[120],"of":[121],"and":[125,143],"every":[129],"sample.":[130],"We":[131],"theoretically":[132],"prove":[133],"guidance":[136],"provided":[137],"by":[138],"our":[139],"method":[140],"rational":[142],"near-optimal.":[144],"Extensive":[145],"experiments":[146],"various":[148],"environments":[149],"suggest":[150],"can":[153],"easily":[155],"installed":[156],"most":[158],"algorithms":[161],"statistically":[163],"significant":[164],"performance":[165],"improvements.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}