{"id":"https://openalex.org/W4386524114","doi":"https://doi.org/10.1109/tnnls.2023.3309906","title":"Mild Policy Evaluation for Offline Actor\u2013Critic","display_name":"Mild Policy Evaluation for Offline Actor\u2013Critic","publication_year":2023,"publication_date":"2023-09-07","ids":{"openalex":"https://openalex.org/W4386524114","doi":"https://doi.org/10.1109/tnnls.2023.3309906","pmid":"https://pubmed.ncbi.nlm.nih.gov/37676802"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3309906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3309906","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/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002412202","display_name":"Botao Dong","orcid":"https://orcid.org/0000-0002-2026-6856"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Dong","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654848","display_name":"Jinhui Lu","orcid":"https://orcid.org/0000-0003-3291-3288"},"institutions":[{"id":"https://openalex.org/I4210097049","display_name":"Shanghai Ship and Shipping Research Institute","ror":"https://ror.org/00z9npm78","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210097049"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Lu","raw_affiliation_strings":["Shanghai Ship and Shipping Research Institute Company Ltd., Shanghai, China","Shanghai Ship and Shipping Research Institute Company Ltd, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Ship and Shipping Research Institute Company Ltd., Shanghai, China","institution_ids":["https://openalex.org/I4210097049"]},{"raw_affiliation_string":"Shanghai Ship and Shipping Research Institute Company Ltd, Shanghai, China","institution_ids":["https://openalex.org/I4210097049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","School of Information and Communication Engineering, Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Information and Communication Engineering, Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5713,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86129191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"35","issue":"12","first_page":"17950","last_page":"17964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8888999819755554,"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":0.8888999819755554,"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":0.049400001764297485,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012400000356137753,"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/computer-science","display_name":"Computer science","score":0.3959851562976837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3959851562976837}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3309906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3309906","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:37676802","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37676802","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":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1852921944","display_name":null,"funder_award_id":"2022ZD0119903","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5721963804","display_name":null,"funder_award_id":"U2141234","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2754517384","https://openalex.org/W2963077474","https://openalex.org/W2981211936","https://openalex.org/W2989958156","https://openalex.org/W3000642679","https://openalex.org/W3170422092","https://openalex.org/W3175891031","https://openalex.org/W3185083385","https://openalex.org/W3207654079","https://openalex.org/W3212538202","https://openalex.org/W3212622989","https://openalex.org/W4214717370","https://openalex.org/W4289792723","https://openalex.org/W4295308578","https://openalex.org/W4297095626","https://openalex.org/W4308364487","https://openalex.org/W4312753915","https://openalex.org/W4360584316","https://openalex.org/W6679100793","https://openalex.org/W6683300800","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6790644358","https://openalex.org/W6791377749","https://openalex.org/W6791981239","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6802586024","https://openalex.org/W6802659552","https://openalex.org/W6803383913","https://openalex.org/W6839066311","https://openalex.org/W6840739175"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,56],"offline":[1,39,87,111,120,135,189],"actor-critic":[2],"(AC)":[3],"algorithms,":[4,137],"the":[5,9,68,71,77,86,92,95,98,103,107,110,138,147,154,159,170,175,180,187],"distributional":[6],"shift":[7],"between":[8,70,97],"training":[10],"data":[11],"and":[12,80,102,106,179],"target":[13,78],"policy":[14,63,79],"causes":[15],"optimistic":[16],"value":[17,49,100,139,162],"estimates":[18],"for":[19],"out-of-distribution":[20],"(OOD)":[21],"actions.":[22],"This":[23],"leads":[24],"to":[25,52,186],"learned":[26,99],"policies":[27],"skewed":[28],"toward":[29],"OOD":[30],"actions":[31,74,83],"with":[32,113,133],"falsely":[33],"high":[34],"values.":[35],"The":[36,89],"existing":[37,134],"value-regularized":[38],"AC":[40,112,121,136],"algorithms":[41],"address":[42],"this":[43,57],"issue":[44],"by":[45,66,76,126,146],"learning":[46,191],"a":[47,53,61],"conservative":[48],"function,":[50],"leading":[51],"performance":[54,181],"drop.":[55],"article,":[58],"we":[59],"propose":[60],"mild":[62,119],"evaluation":[64],"(MPE)":[65],"constraining":[67],"difference":[69],"values":[72],"of":[73,82,91,109,142,149,156,177,183],"supported":[75],"those":[81],"contained":[84],"within":[85],"dataset.":[88],"convergence":[90],"proposed":[93],"MPE,":[94],"gap":[96,141],"function":[101,140,163],"true":[104,160],"one,":[105],"suboptimality":[108],"MPE":[114,128,178],"are":[115],"analyzed,":[116],"respectively.":[117],"A":[118],"(MOAC)":[122],"algorithm":[123],"is":[124,144],"developed":[125],"integrating":[127],"into":[129],"off-policy":[130],"AC.":[131],"Compared":[132],"MOAC":[143,184],"bounded":[145],"existence":[148],"sampling":[150,157],"errors.":[151],"Moreover,":[152],"in":[153],"absence":[155],"errors,":[158],"state":[161],"can":[164],"be":[165],"obtained.":[166],"Experimental":[167],"results":[168],"on":[169],"D4RL":[171],"benchmark":[172],"dataset":[173],"demonstrate":[174],"effectiveness":[176],"superiority":[182],"compared":[185],"state-of-the-art":[188],"reinforcement":[190],"(RL)":[192],"algorithms.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}