{"id":"https://openalex.org/W4385656622","doi":"https://doi.org/10.1109/tsmc.2023.3296773","title":"Ask-AC: An Initiative Advisor-in-the-Loop Actor\u2013Critic Framework","display_name":"Ask-AC: An Initiative Advisor-in-the-Loop Actor\u2013Critic Framework","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4385656622","doi":"https://doi.org/10.1109/tsmc.2023.3296773"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2023.3296773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3296773","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shunyu Liu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632847","display_name":"Kaixuan Chen","orcid":"https://orcid.org/0000-0002-2492-5230"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968615","display_name":"Na Yu","orcid":"https://orcid.org/0009-0008-5499-5388"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Yu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047371218","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-3671-6521"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043914348","display_name":"Zunlei Feng","orcid":"https://orcid.org/0000-0001-8640-8434"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunlei Feng","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090854835"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.5254,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71076233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"53","issue":"12","first_page":"7403","last_page":"7414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9836999773979187,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.9438557028770447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7251847386360168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6749451160430908},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6073302626609802},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5831505060195923},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5186387896537781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4594349265098572},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.426790714263916},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4267004132270813},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4002003073692322},{"id":"https://openalex.org/keywords/process-management","display_name":"Process management","score":0.3305051922798157},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1872226595878601},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1853131651878357},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.16113439202308655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09222045540809631}],"concepts":[{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.9438557028770447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7251847386360168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6749451160430908},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6073302626609802},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5831505060195923},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5186387896537781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4594349265098572},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.426790714263916},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4267004132270813},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4002003073692322},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.3305051922798157},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1872226595878601},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1853131651878357},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.16113439202308655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09222045540809631},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2023.3296773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3296773","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8658505043","display_name":null,"funder_award_id":"2018AAA0101503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335984","display_name":"Science and Technology Foundation of State Grid Corporation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1986014385","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2156869222","https://openalex.org/W2604382266","https://openalex.org/W2604618034","https://openalex.org/W2620645529","https://openalex.org/W2736601468","https://openalex.org/W2788862220","https://openalex.org/W2837981523","https://openalex.org/W2914225466","https://openalex.org/W2921955147","https://openalex.org/W2962787969","https://openalex.org/W2963390684","https://openalex.org/W2963489214","https://openalex.org/W2964407556","https://openalex.org/W2964654516","https://openalex.org/W2965723696","https://openalex.org/W2978382466","https://openalex.org/W2982316857","https://openalex.org/W2996868001","https://openalex.org/W3034311880","https://openalex.org/W3045372678","https://openalex.org/W3109289797","https://openalex.org/W3115597439","https://openalex.org/W4214717370","https://openalex.org/W6631533588","https://openalex.org/W6674812091","https://openalex.org/W6679700999","https://openalex.org/W6684921986","https://openalex.org/W6685726866","https://openalex.org/W6692846177","https://openalex.org/W6696265566","https://openalex.org/W6718092244","https://openalex.org/W6730844258","https://openalex.org/W6732417791","https://openalex.org/W6732837357","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6751285671","https://openalex.org/W6758933963","https://openalex.org/W6797377937","https://openalex.org/W6797805595","https://openalex.org/W6799946856","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2515552481","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W156769215","https://openalex.org/W4308101915","https://openalex.org/W3194047734","https://openalex.org/W2251005117","https://openalex.org/W2396112788"],"abstract_inverted_index":{"Despite":[0],"the":[1,20,56,79,108,116,122,125,131,142,163,168,172,176],"promising":[2],"results":[3,149],"achieved,":[4],"state-of-the-art":[5],"interactive":[6],"reinforcement":[7],"learning":[8,37,169],"schemes":[9],"rely":[10],"on":[11,145,150,178],"passively":[12],"receiving":[13],"supervision":[14],"signals":[15],"from":[16],"advisor":[17,113,185],"experts,":[18],"in":[19,32,115],"form":[21],"of":[22,81,118,171],"either":[23],"continuous":[24,184],"monitoring":[25],"or":[26],"predefined":[27],"rules,":[28],"which":[29],"inevitably":[30],"result":[31],"a":[33,44,61,68],"cumbersome":[34],"and":[35,65,70,76,90,137,153,156,174],"expensive":[36],"process.":[38],"In":[39],"this":[40],"article,":[41],"we":[42],"introduce":[43],"novel":[45],"initiative":[46],"advisor-in-the-loop":[47],"actor\u2013critic":[48],"(AC)":[49],"framework,":[50],"termed":[51],"as":[52],"Ask-AC,":[53],"that":[54,94,162],"replaces":[55],"unilateral":[57],"advisor-guidance":[58],"mechanism":[59],"with":[60,180],"bidirectional":[62],"learner-initiative":[63],"one,":[64],"thereby":[66],"enables":[67],"customized":[69],"efficacious":[71],"message":[72],"exchange":[73],"between":[74],"learner":[75],"advisor.":[77],"At":[78],"heart":[80],"Ask-AC":[82],"are":[83],"two":[84],"complementary":[85],"components,":[86],"namely,":[87],"action":[88,144],"requester":[89],"adaptive":[91],"state":[92],"selector,":[93],"can":[95],"be":[96],"readily":[97],"incorporated":[98],"into":[99],"various":[100],"discrete":[101],"AC":[102,159],"architectures.":[103],"The":[104],"former":[105,132],"component":[106],"allows":[107],"agent":[109],"to":[110,140],"initiatively":[111],"seek":[112],"intervention":[114],"presence":[117],"uncertain":[119],"states,":[120],"while":[121],"latter":[123],"identifies":[124],"unstable":[126],"states":[127],"potentially":[128],"missed":[129],"by":[130,183],"especially":[133],"when":[134],"environment":[135],"changes,":[136],"then":[138],"learns":[139],"promote":[141],"ask":[143],"such":[146],"states.":[147],"Experimental":[148],"both":[151],"stationary":[152],"nonstationary":[154],"environments":[155],"across":[157],"different":[158],"backbones":[160],"demonstrate":[161],"proposed":[164],"framework":[165],"significantly":[166],"improves":[167],"efficiency":[170],"agent,":[173],"achieves":[175],"performances":[177],"par":[179],"those":[181],"obtained":[182],"monitoring.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
