{"id":"https://openalex.org/W4392903325","doi":"https://doi.org/10.1109/icassp48485.2024.10446266","title":"Offline Reinforcement Learning with Generative Adversarial Networks and Uncertainty Estimation","display_name":"Offline Reinforcement Learning with Generative Adversarial Networks and Uncertainty Estimation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903325","doi":"https://doi.org/10.1109/icassp48485.2024.10446266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446266","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":"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/A5108030925","display_name":"Lan Wu","orcid":"https://orcid.org/0000-0003-0892-6601"},"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":true,"raw_author_name":"Lan Wu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Soochow,China","School of Computer Science and Technology, Soochow University, Soochow, China"],"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","School of Computer Science and Technology, Soochow University, Soochow, China","Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Soochow, China"],"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"]},{"raw_affiliation_string":"Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Soochow, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022500357","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0002-1923-2173"},"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"],"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":"last","author":{"id":"https://openalex.org/A5086179182","display_name":"Zhigang Huang","orcid":"https://orcid.org/0000-0003-1959-2192"},"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":"Zhigang Huang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Soochow,China","School of Computer Science and Technology, Soochow University, Soochow, China"],"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":4,"corresponding_author_ids":["https://openalex.org/A5108030925"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":1.3264,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8243887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5255","last_page":"5259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9939000010490417,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8130795955657959},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6794352531433105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6703103184700012},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6482406854629517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6254246830940247},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6048275232315063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5932284593582153},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5753622055053711},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5411038398742676},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42567774653434753},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34340453147888184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18685272336006165},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10872238874435425}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8130795955657959},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6794352531433105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6703103184700012},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6482406854629517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254246830940247},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6048275232315063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5932284593582153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5753622055053711},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5411038398742676},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42567774653434753},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34340453147888184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18685272336006165},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10872238874435425},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446266","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":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W4360584316","https://openalex.org/W4360987160","https://openalex.org/W4383108498","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771217966","https://openalex.org/W6774583691","https://openalex.org/W6779265984","https://openalex.org/W6785559887","https://openalex.org/W6792049622","https://openalex.org/W6796183756","https://openalex.org/W6800238617","https://openalex.org/W6801801719","https://openalex.org/W6810030924","https://openalex.org/W6810203658","https://openalex.org/W6811051195","https://openalex.org/W6846142413"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"In":[0,123],"recent":[1],"years,":[2],"offline":[3,50],"reinforcement":[4,51],"learning":[5,52],"has":[6],"attracted":[7],"considerable":[8],"attention":[9],"in":[10,27],"artificial":[11],"intelligence.":[12],"By":[13],"generating":[14],"a":[15,19,82],"static":[16],"dataset":[17],"through":[18,88],"behavior":[20],"policy,":[21],"it":[22],"is":[23,61],"unable":[24],"to":[25,37],"engage":[26],"online":[28],"interactions":[29],"with":[30,53],"the":[31,47,66,73,86,94,101,115,131,134],"environment.":[32],"However,":[33],"this":[34],"inevitably":[35],"leads":[36],"states":[38],"or":[39],"actions":[40],"undergoing":[41],"inherent":[42],"distribution":[43],"shifts.":[44],"To":[45],"address":[46],"above":[48],"concerns,":[49],"generative":[54,68],"adversarial":[55,69],"networks":[56,70],"and":[57,71,117],"uncertainty":[58,90],"estimation":[59],"(GANUE)":[60],"proposed.":[62],"This":[63],"approach":[64],"parameterizes":[65],"conditional":[67],"avoids":[72],"over-constraint":[74],"problem":[75],"that":[76,109],"would":[77],"be":[78],"introduced":[79],"when":[80],"using":[81],"distance":[83],"metric.":[84],"Estimating":[85],"Q-value":[87],"ensemble":[89],"not":[91],"only":[92],"relaxes":[93],"policy":[95],"constraint":[96],"strength":[97],"but":[98],"also":[99],"enhances":[100],"out-of-distribution":[102],"generalization":[103],"ability.":[104],"The":[105],"experimental":[106],"results":[107],"show":[108],"GANUE":[110],"significantly":[111],"performs":[112],"better":[113],"on":[114],"Maze2D":[116],"Adroit":[118],"tasks":[119],"than":[120],"multiple":[121],"baselines.":[122],"addition,":[124],"we":[125],"perform":[126],"sensitivity":[127],"analysis":[128],"experiments":[129],"for":[130],"parameters":[132],"of":[133],"perturbation":[135],"model.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}