{"id":"https://openalex.org/W4400070556","doi":"https://doi.org/10.1109/tii.2024.3413308","title":"Offline Reinforcement Learning With Reverse Diffusion Guide Policy","display_name":"Offline Reinforcement Learning With Reverse Diffusion Guide Policy","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400070556","doi":"https://doi.org/10.1109/tii.2024.3413308"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2024.3413308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3413308","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-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/A5101885863","display_name":"Jiazhi Zhang","orcid":"https://orcid.org/0009-0009-8963-6374"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Zhang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8963-6374","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004354148","display_name":"Shuo Cao","orcid":"https://orcid.org/0000-0003-3998-461X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Cao","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3998-461X","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":1.3577,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80254394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"20","issue":"10","first_page":"11785","last_page":"11793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9345999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9345999956130981,"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/T14011","display_name":"Elevator Systems and Control","score":0.9318000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6307350993156433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.582431435585022},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4872500002384186},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4151093363761902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3887374699115753},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17404994368553162},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08524107933044434}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6307350993156433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582431435585022},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4872500002384186},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4151093363761902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3887374699115753},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17404994368553162},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08524107933044434},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2024.3413308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3413308","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4823360002","display_name":null,"funder_award_id":"62373364","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2973229164","https://openalex.org/W2979211489","https://openalex.org/W2991355586","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3205794883","https://openalex.org/W4205359845","https://openalex.org/W4220774516","https://openalex.org/W4225659902","https://openalex.org/W4226376398","https://openalex.org/W4291960900","https://openalex.org/W4293327156","https://openalex.org/W4298183794","https://openalex.org/W4308242490","https://openalex.org/W4312281895","https://openalex.org/W4320015828","https://openalex.org/W4360884927","https://openalex.org/W4384499218","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6768617876","https://openalex.org/W6771270455","https://openalex.org/W6779265984","https://openalex.org/W6779823529","https://openalex.org/W6780159193","https://openalex.org/W6780964083","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6792049622","https://openalex.org/W6795288823","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6811291704","https://openalex.org/W6838327568","https://openalex.org/W6841549819","https://openalex.org/W6842958722","https://openalex.org/W6843816287","https://openalex.org/W6846913117","https://openalex.org/W6847106716","https://openalex.org/W6852572940","https://openalex.org/W6853588135","https://openalex.org/W6858393028","https://openalex.org/W6870219138"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(ORL)":[3],"learns":[4],"policy":[5,51,69,99,110,136,169],"from":[6],"a":[7,91,101,106,154],"static":[8],"dataset":[9],"without":[10],"further":[11,159],"interaction":[12,28],"with":[13,77,100],"the":[14,35,49,56,67,81,97,113,132,140,147,162,167,171,184,187],"environment,":[15],"which":[16,95],"holds":[17],"significant":[18],"promise":[19],"in":[20,117],"industrial":[21],"control":[22],"systems":[23],"characterized":[24],"by":[25,39],"inefficient":[26],"online":[27],"and":[29,71,104,126,131],"inherent":[30],"safety":[31],"concerns.":[32],"To":[33],"mitigate":[34],"extrapolation":[36],"error":[37],"induced":[38],"distribution":[40,128],"shift,":[41],"it":[42],"is":[43],"essential":[44],"for":[45],"ORL":[46,93,193],"to":[47,52,65,74,111,144,161,165],"constrain":[48],"learned":[50,86,168],"perform":[53],"actions":[54,76],"within":[55,80],"support":[57,82,142],"set":[58,143],"of":[59,174,186],"behavior":[60,68,98,175],"policy.":[61,87,176],"Existing":[62],"methods":[63],"fail":[64],"represent":[66],"properly":[70],"typically":[72],"tend":[73],"prefer":[75],"higher":[78],"densities":[79],"set,":[83],"resulting":[84],"suboptimal":[85],"This":[88],"article":[89],"proposes":[90],"novel":[92],"method":[94],"represents":[96],"diffusion":[102,108,115,121,134],"model":[103,116,122],"trains":[105],"reverse":[107,133],"guide":[109,135],"instruct":[112],"pretrained":[114],"generating":[118],"actions.":[119],"The":[120],"exhibits":[123],"stable":[124],"training":[125],"strong":[127],"expression":[129],"ability,":[130],"can":[137,157],"effectively":[138],"explore":[139],"entire":[141],"help":[145,166],"generate":[146],"optimal":[148],"action.":[149],"When":[150],"facing":[151],"low-quality":[152],"datasets,":[153],"trainable":[155],"perturbation":[156],"be":[158],"added":[160],"generated":[163],"action":[164],"escape":[170],"performance":[172],"limitation":[173],"Experimental":[177],"results":[178],"on":[179],"D4RL":[180],"Gym-MuJoCo":[181],"benchmark":[182],"demonstrate":[183],"effectiveness":[185],"proposed":[188],"method,":[189],"surpassing":[190],"several":[191],"state-of-the-art":[192],"methods.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}