{"id":"https://openalex.org/W4392903933","doi":"https://doi.org/10.1109/icassp48485.2024.10447908","title":"Offline Reinforcement Learning with Policy Guidance and Uncertainty Estimation","display_name":"Offline Reinforcement Learning with Policy Guidance and Uncertainty Estimation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903933","doi":"https://doi.org/10.1109/icassp48485.2024.10447908"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447908","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447908","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","Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, 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":"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":"middle","author":{"id":"https://openalex.org/A5100414890","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0001-5770-9529"},"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":0.3316,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61037439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5010","last_page":"5014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9927999973297119,"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":0.9904999732971191,"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/generalization","display_name":"Generalization","score":0.8709763288497925},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8104063868522644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.674994945526123},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6029698848724365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234453082084656},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4705662429332733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4673120677471161},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4133968949317932},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40189364552497864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20365849137306213},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07775723934173584}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8709763288497925},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8104063868522644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.674994945526123},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6029698848724365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234453082084656},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4705662429332733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4673120677471161},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4133968949317932},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40189364552497864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20365849137306213},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07775723934173584},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447908","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447908","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3016525976","https://openalex.org/W4283324682","https://openalex.org/W4283796596","https://openalex.org/W4313420431","https://openalex.org/W4315778373","https://openalex.org/W4360584316","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771217966","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6785559887","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6801801719","https://openalex.org/W6810030924","https://openalex.org/W6810602712","https://openalex.org/W6811554491","https://openalex.org/W6838356327"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1,62],"learning":[2,63],"is":[3,71,98],"an":[4],"approach":[5,48,78],"for":[6],"transforming":[7],"static":[8],"datasets":[9],"into":[10,117],"powerful":[11],"decision":[12],"engines.":[13],"It":[14],"cannot":[15],"interact":[16],"with":[17,64],"the":[18,33,41,51,58,81,93,101,105,118,122,128,140],"environment":[19],"online,":[20],"which":[21],"leads":[22],"to":[23,40],"distribution":[24,142],"shifts.":[25],"Previous":[26],"approaches":[27],"addressed":[28],"this":[29,45],"problem":[30],"by":[31],"making":[32],"current":[34],"policy":[35,65],"as":[36,38],"close":[37],"possible":[39],"behavior":[42],"policy.":[43,112],"However,":[44],"type":[46],"of":[47,54,84,92,96,104,125],"severely":[49],"limits":[50],"generalization":[52,82,95,124,146],"ability":[53,83],"Q-functions.":[55,126],"To":[56],"address":[57],"above":[59],"concerns,":[60],"offline":[61],"guidance":[66,103],"and":[67,143],"uncertainty":[68,115],"estimation":[69,116],"(PGUE)":[70],"proposed.":[72],"PGUE":[73,131],"proposes":[74],"a":[75,87,109],"fine-grained":[76],"adjustment":[77],"that":[79],"improves":[80,121],"Q-functions":[85,97],"using":[86],"perturbation":[88],"model.":[89],"The":[90],"enhancement":[91],"out-of-distribution":[94,145],"achieved":[99],"through":[100],"implicit":[102],"state":[106,141],"space":[107],"via":[108],"deterministic":[110],"latent":[111],"Meanwhile,":[113],"integrating":[114],"loss":[119],"function":[120],"in-distribution":[123],"On":[127],"D4RL":[129],"benchmark,":[130],"has":[132],"better":[133],"performance":[134],"than":[135],"baselines.":[136],"Moreover,":[137],"we":[138],"verify":[139],"its":[144],"ability.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}