{"id":"https://openalex.org/W3119399317","doi":"https://doi.org/10.1109/cdc42340.2020.9304004","title":"Self-Guided Actor-Critic: Reinforcement Learning from Adaptive Expert Demonstrations","display_name":"Self-Guided Actor-Critic: Reinforcement Learning from Adaptive Expert Demonstrations","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3119399317","doi":"https://doi.org/10.1109/cdc42340.2020.9304004","mag":"3119399317"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100340490","display_name":"Haoran Zhang","orcid":"https://orcid.org/0000-0002-6883-1375"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055805014","display_name":"Chenkun Yin","orcid":"https://orcid.org/0000-0002-7878-4824"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenkun Yin","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621515","display_name":"Yanxin Zhang","orcid":"https://orcid.org/0000-0002-1767-7371"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxin Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015052103","display_name":"Shangtai Jin","orcid":"https://orcid.org/0000-0003-0986-6604"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangtai Jin","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"572","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9735000133514404,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9154996871948242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7502474784851074},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.619319498538971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5909286141395569},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5187440514564514},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43060699105262756},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4249924123287201}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9154996871948242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502474784851074},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.619319498538971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909286141395569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5187440514564514},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43060699105262756},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4249924123287201},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W112666333","https://openalex.org/W1923344279","https://openalex.org/W1931877416","https://openalex.org/W2016211524","https://openalex.org/W2024691747","https://openalex.org/W2104733512","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2345644119","https://openalex.org/W2609650878","https://openalex.org/W2741122588","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2805805280","https://openalex.org/W2904453761","https://openalex.org/W2962872206","https://openalex.org/W2962902376","https://openalex.org/W2962957031","https://openalex.org/W2963376229","https://openalex.org/W2963477884","https://openalex.org/W2963704132","https://openalex.org/W2963864421","https://openalex.org/W2964070888","https://openalex.org/W2998396902","https://openalex.org/W4297664295","https://openalex.org/W4302570325","https://openalex.org/W6604566608","https://openalex.org/W6640174482","https://openalex.org/W6675999342","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6736495777","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748645729","https://openalex.org/W6751275834","https://openalex.org/W6751285671","https://openalex.org/W6757469721","https://openalex.org/W6770232462"],"related_works":["https://openalex.org/W2384667405","https://openalex.org/W2389266787","https://openalex.org/W2363885542","https://openalex.org/W2387206255","https://openalex.org/W2355570285","https://openalex.org/W2364958354","https://openalex.org/W2352797113","https://openalex.org/W1548050717","https://openalex.org/W2372137583","https://openalex.org/W117598325"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3],"novel":[4],"Reinforcement":[5,22,146],"Learning":[6,23,147],"from":[7,28],"Demonstration":[8],"(RLfD)":[9],"algorithm,":[10],"called":[11],"Self-Guided":[12],"Actor-Critic":[13],"(SGAC),":[14],"with":[15],"the":[16,77,97,101,110,135],"purpose":[17],"of":[18,21,32,44,80,100,113,121,138],"enhancing":[19],"exploration":[20],"by":[24,55,66],"imitating":[25],"expert":[26,52,62,102,112],"policies":[27],"demonstration":[29],"data.":[30],"Instead":[31],"using":[33],"human":[34],"experts":[35],"or":[36],"other":[37],"control":[38,127],"algorithms":[39,148],"as":[40],"demonstrations":[41],"in":[42,103],"most":[43],"existing":[45],"methods,":[46],"SGAC":[47,81,114,123,139],"can":[48,115],"generate":[49],"high":[50],"quality":[51],"data":[53],"online":[54],"continuously":[56],"querying":[57],"and":[58,84,142,149],"adaptively":[59],"updating":[60],"an":[61],"that":[63],"is":[64,82,93,107,129,140],"given":[65],"model":[67],"predictive":[68],"Deep":[69],"Deterministic":[70],"Policy":[71],"Gradient":[72],"(MP-DDPG).":[73],"In":[74,95],"this":[75],"way,":[76],"training":[78],"cost":[79],"reduced,":[83],"distribution":[85],"mismatch":[86],"problem":[87,128],"leading":[88],"to":[89,124],"unstable":[90],"learning":[91,136],"process":[92,137],"alleviated.":[94],"addition,":[96],"optimality":[98],"assumption":[99],"typical":[104,145],"RLfD":[105],"methods":[106],"relaxed":[108],"since":[109],"adaptive":[111],"make":[116],"self-improvement.":[117],"A":[118],"non-trivial":[119],"example":[120],"applying":[122],"ship":[125],"berthing":[126],"present.":[130],"The":[131],"simulation":[132],"results":[133],"show":[134],"faster":[141],"steadier":[143],"than":[144],"MP-DDPG.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}