{"id":"https://openalex.org/W4405179546","doi":"https://doi.org/10.1109/tnnls.2024.3493113","title":"Generative Adversarial Soft Actor\u2013Critic","display_name":"Generative Adversarial Soft Actor\u2013Critic","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405179546","doi":"https://doi.org/10.1109/tnnls.2024.3493113","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030452"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3493113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3493113","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/A5046284028","display_name":"Hyo-Seok Hwang","orcid":"https://orcid.org/0000-0002-5908-0944"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyo-Seok Hwang","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5908-0944","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008851484","display_name":"Yoojoong Kim","orcid":"https://orcid.org/0000-0002-6615-9116"},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoojoong Kim","raw_affiliation_strings":["School of Computer Science and Information Engineering, The Catholic University of Korea, Bucheon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6615-9116","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, The Catholic University of Korea, Bucheon, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069534195","display_name":"Junhee Seok","orcid":"https://orcid.org/0000-0002-6475-8457"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhee Seok","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6475-8457","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046284028"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.9828,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88870718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"36","issue":"7","first_page":"11917","last_page":"11927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8030978441238403},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7640209197998047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6627035140991211},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6428190469741821},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5860525965690613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47283703088760376},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4345201253890991},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35790279507637024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.250241756439209}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8030978441238403},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7640209197998047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6627035140991211},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6428190469741821},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5860525965690613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47283703088760376},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4345201253890991},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35790279507637024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.250241756439209},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3493113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3493113","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:40030452","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030452","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":[],"awards":[{"id":"https://openalex.org/G2882647077","display_name":null,"funder_award_id":"2022R1A2C2004003","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4247106942","display_name":null,"funder_award_id":"IO201214-08149-01","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1503398984","https://openalex.org/W1996881001","https://openalex.org/W2090346540","https://openalex.org/W2158782408","https://openalex.org/W2166944917","https://openalex.org/W2593414223","https://openalex.org/W2782599016","https://openalex.org/W2904246096","https://openalex.org/W2962770929","https://openalex.org/W2963748089","https://openalex.org/W2990440529","https://openalex.org/W2990747716","https://openalex.org/W3018536089","https://openalex.org/W3027406032","https://openalex.org/W3121342653","https://openalex.org/W3150807214","https://openalex.org/W3204937802","https://openalex.org/W4212863985","https://openalex.org/W4288046472","https://openalex.org/W4297964528","https://openalex.org/W4312933868","https://openalex.org/W4385535562","https://openalex.org/W4390873054","https://openalex.org/W6635084905","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6678815747","https://openalex.org/W6683001934","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6714644935","https://openalex.org/W6717434760","https://openalex.org/W6730111887","https://openalex.org/W6731259203","https://openalex.org/W6734517396","https://openalex.org/W6738125122","https://openalex.org/W6738706147","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6741832134","https://openalex.org/W6743668032","https://openalex.org/W6743802245","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6748839928","https://openalex.org/W6752910514","https://openalex.org/W6755137159","https://openalex.org/W6763213874","https://openalex.org/W6766512961","https://openalex.org/W6770847983","https://openalex.org/W6771256060","https://openalex.org/W6775002472","https://openalex.org/W6780559895","https://openalex.org/W6791623595","https://openalex.org/W6803601828","https://openalex.org/W6810672005","https://openalex.org/W6811291704","https://openalex.org/W6838639034"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"In":[0,77,111],"deep":[1],"reinforcement":[2],"learning":[3,5],"(RL),":[4],"stochastic":[6,37],"and":[7,98,123,142,154],"multimodal":[8,152],"policies":[9],"are":[10],"crucial":[11],"for":[12,54,88,108],"various":[13,125],"tasks,":[14],"but":[15,66],"most":[16],"continuous":[17,144],"control":[18,145],"algorithms":[19],"model":[20,151],"the":[21,40,61,64,71,74,82,93,129],"policy":[22,38,53,65,153,156],"using":[23],"a":[24,36,50,101,115,133],"deterministic":[25],"or":[26],"unimodal":[27],"Gaussian":[28,52],"distribution.":[29],"Despite":[30],"being":[31],"designed":[32],"to":[33],"inherently":[34],"learn":[35,155],"under":[39],"maximum":[41],"entropy":[42],"RL":[43],"framework,":[44],"soft":[45],"actor-critic":[46],"(SAC)":[47],"also":[48,67],"uses":[49],"factorized":[51],"tractable":[55],"optimization,":[56],"which":[57],"not":[58],"only":[59],"restricts":[60],"expressiveness":[62],"of":[63,73,84,95,161],"ignores":[68],"correlations":[69],"among":[70],"components":[72],"action":[75],"vector.":[76],"this":[78],"article,":[79],"we":[80,113],"revisit":[81],"approach":[83],"employing":[85],"normalizing":[86],"flow":[87],"SAC":[89,109,118],"policy,":[90],"justified":[91],"by":[92],"change":[94],"variable":[96],"theorem,":[97],"then":[99],"propose":[100],"state-dependent":[102],"nonvolume":[103],"preserving":[104],"(SD-NVP)":[105],"architecture":[106],"suitable":[107],"learning.":[110],"addition,":[112],"introduce":[114],"generative":[116,134],"adversarial":[117,135],"(GASAC)":[119],"that":[120,149],"implicitly":[121],"defines":[122],"optimizes":[124],"divergences":[126],"without":[127],"calculating":[128],"normalization":[130],"constant":[131],"through":[132],"loss.":[136],"Experimental":[137],"results":[138],"on":[139],"multigoal":[140],"environment":[141],"MuJoCo":[143],"tasks":[146],"suite":[147],"demonstrate":[148],"GASAC":[150],"more":[157],"stably":[158],"in":[159],"terms":[160],"cumulative":[162],"return.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}