{"id":"https://openalex.org/W7127313521","doi":"https://doi.org/10.1109/jas.2025.125633","title":"Offline Generalized Actor-Critic with Distance Regularization","display_name":"Offline Generalized Actor-Critic with Distance Regularization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127313521","doi":"https://doi.org/10.1109/jas.2025.125633"},"language":null,"primary_location":{"id":"doi:10.1109/jas.2025.125633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2025.125633","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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/A5107746163","display_name":"Huanting Feng","orcid":null},"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":"Huanting Feng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"],"raw_orcid":"https://orcid.org/0009-0009-2538-4761","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124927443","display_name":"Yuhu Cheng","orcid":null},"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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"],"raw_orcid":"https://orcid.org/0000-0003-0636-5820","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":null,"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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11844198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"1","first_page":"57","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6578999757766724,"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":0.6578999757766724,"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":0.26649999618530273,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.013100000098347664,"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/regularization","display_name":"Regularization (linguistics)","score":0.6603000164031982},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5892000198364258},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.40630000829696655},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4050000011920929},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3946000039577484},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.3718999922275543},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6603000164031982},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5388000011444092},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4555000066757202},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40560001134872437},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jas.2025.125633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2025.125633","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6758348345756531}],"awards":[{"id":"https://openalex.org/G4139182756","display_name":null,"funder_award_id":"62373364,62176259","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2766447205","https://openalex.org/W3092253573","https://openalex.org/W3119186746","https://openalex.org/W3127561923","https://openalex.org/W3135203571","https://openalex.org/W3185083385","https://openalex.org/W3187550742","https://openalex.org/W3210408793","https://openalex.org/W3216656735","https://openalex.org/W4280520183","https://openalex.org/W4307230233","https://openalex.org/W4360584316","https://openalex.org/W4362722548","https://openalex.org/W4378805020","https://openalex.org/W4384644208","https://openalex.org/W4386524114","https://openalex.org/W4390887444","https://openalex.org/W4391305708"],"related_works":[],"abstract_inverted_index":{"In":[0,50],"order":[1],"to":[2,107],"address":[3],"the":[4,16,21,56,64,67,143],"issue":[5],"of":[6,18,58,99,147],"overly":[7],"conservative":[8,153],"offline":[9,80,154],"reinforcement":[10],"learning":[11,95],"(RL)":[12],"methods":[13],"that":[14,63,122,137],"limit":[15],"generalization":[17],"policy":[19,127],"in":[20],"out-of-distribution":[22],"(OOD)":[23],"region,":[24],"this":[25],"article":[26],"designs":[27],"a":[28,41,125],"surrogate":[29],"target":[30],"for":[31],"OOD":[32],"value":[33,75],"function":[34],"based":[35],"on":[36,131],"dataset":[37],"distance":[38,47,85,113],"and":[39,72,102,110,116,145],"proposes":[40],"novel":[42],"generalized":[43,81],"Q-learning":[44],"mechanism":[45],"with":[46,84,93],"regularization":[48,86],"(GQDR).":[49],"theory,":[51],"we":[52],"not":[53,140],"only":[54,141],"prove":[55],"convergence":[57],"GQDR,":[59],"but":[60,150],"also":[61,151],"ensure":[62],"difference":[65],"between":[66],"Q-value":[68,148],"learned":[69],"by":[70,90],"GQDR":[71,92],"its":[73],"true":[74],"is":[76,88],"bounded.":[77],"Furthermore,":[78],"an":[79],"actor-critic":[82,94],"method":[83],"(OGACDR)":[87],"proposed":[89],"combining":[91],"framework.":[96],"Two":[97],"implementations":[98],"OGACDR,":[100],"OGACDR-EXP":[101],"OGACDR-SQR,":[103],"are":[104],"introduced":[105],"according":[106],"exponential":[108],"(EXP)":[109],"open-square":[111],"(SQR)":[112],"weight":[114],"functions,":[115],"it":[117],"has":[118],"been":[119],"theoretically":[120],"proved":[121],"OGACDR":[123,138],"provides":[124],"safe":[126],"improvement.":[128],"Experimental":[129],"results":[130],"Gym-MuJoCo":[132],"continuous":[133],"control":[134],"tasks":[135],"show":[136],"can":[139],"alleviate":[142],"overestimation":[144],"overconservatism":[146],"function,":[149],"outperform":[152],"RL":[155],"baselines.":[156]},"counts_by_year":[],"updated_date":"2026-02-06T02:01:19.302388","created_date":"2026-02-04T00:00:00"}