{"id":"https://openalex.org/W2940839032","doi":"https://doi.org/10.3390/sym11040590","title":"Supervised Reinforcement Learning via Value Function","display_name":"Supervised Reinforcement Learning via Value Function","publication_year":2019,"publication_date":"2019-04-24","ids":{"openalex":"https://openalex.org/W2940839032","doi":"https://doi.org/10.3390/sym11040590","mag":"2940839032"},"language":"en","primary_location":{"id":"doi:10.3390/sym11040590","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11040590","pdf_url":"https://www.mdpi.com/2073-8994/11/4/590/pdf?version=1556098421","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/11/4/590/pdf?version=1556098421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064026404","display_name":"Yaozong Pan","orcid":"https://orcid.org/0000-0002-4442-6332"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaozong Pan","raw_affiliation_strings":["Space Engineering University, 81 Road, Huairou District, Beijing 101400, China"],"affiliations":[{"raw_affiliation_string":"Space Engineering University, 81 Road, Huairou District, Beijing 101400, China","institution_ids":["https://openalex.org/I4210148107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410064","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0003-1749-5874"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Space Engineering University, 81 Road, Huairou District, Beijing 101400, China"],"affiliations":[{"raw_affiliation_string":"Space Engineering University, 81 Road, Huairou District, Beijing 101400, China","institution_ids":["https://openalex.org/I4210148107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058292168","display_name":"Chunhui Yuan","orcid":"https://orcid.org/0000-0003-4382-2541"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhui Yuan","raw_affiliation_strings":["Space Engineering University, 81 Road, Huairou District, Beijing 101400, China"],"affiliations":[{"raw_affiliation_string":"Space Engineering University, 81 Road, Huairou District, Beijing 101400, China","institution_ids":["https://openalex.org/I4210148107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738779","display_name":"Haitao Yang","orcid":"https://orcid.org/0000-0002-0375-0873"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitao Yang","raw_affiliation_strings":["Space Engineering University, 81 Road, Huairou District, Beijing 101400, China"],"affiliations":[{"raw_affiliation_string":"Space Engineering University, 81 Road, Huairou District, Beijing 101400, China","institution_ids":["https://openalex.org/I4210148107"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101738779"],"corresponding_institution_ids":["https://openalex.org/I4210148107"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.03382448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":"4","first_page":"590","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.991599977016449,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9891999959945679,"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":0.8220887184143066},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8216167688369751},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6065389513969421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5874987244606018},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4396216571331024},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42366620898246765},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42064374685287476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35497552156448364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220887184143066},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8216167688369751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6065389513969421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874987244606018},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4396216571331024},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42366620898246765},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42064374685287476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35497552156448364},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym11040590","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11040590","pdf_url":"https://www.mdpi.com/2073-8994/11/4/590/pdf?version=1556098421","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4ab1a00e79064ca3b4a69a537a0761a6","is_oa":true,"landing_page_url":"https://doaj.org/article/4ab1a00e79064ca3b4a69a537a0761a6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 11, Iss 4, p 590 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/11/4/590/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym11040590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym11040590","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11040590","pdf_url":"https://www.mdpi.com/2073-8994/11/4/590/pdf?version=1556098421","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940839032.pdf","grobid_xml":"https://content.openalex.org/works/W2940839032.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W169931978","https://openalex.org/W1873332500","https://openalex.org/W2116001481","https://openalex.org/W2118688707","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2507592741","https://openalex.org/W2553303224","https://openalex.org/W2578206533","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2786800733","https://openalex.org/W2788862220","https://openalex.org/W2962887844","https://openalex.org/W2963099939","https://openalex.org/W2963376229","https://openalex.org/W2963411833","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W3150570724","https://openalex.org/W4394667800","https://openalex.org/W6637967152","https://openalex.org/W6639175750","https://openalex.org/W6682849425","https://openalex.org/W6687681856","https://openalex.org/W6732665253"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2518241345","https://openalex.org/W4390062853","https://openalex.org/W4389256085","https://openalex.org/W4399290976","https://openalex.org/W4285328440","https://openalex.org/W4313644201"],"abstract_inverted_index":{"Using":[0],"expert":[1,37,70,97,149],"samples":[2,71,150],"to":[3,29,107],"improve":[4,140],"the":[5,16,32,41,67,74,86,90,109,132,141,148],"performance":[6,45,143],"of":[7,15,18,36,46,65,89,144],"reinforcement":[8],"learning":[9,81],"(RL)":[10],"algorithms":[11,116],"has":[12],"become":[13],"one":[14],"focuses":[17],"research":[19],"nowadays.":[20],"However,":[21],"in":[22,102,135],"different":[23],"application":[24,43],"scenarios,":[25],"it":[26],"is":[27,58,63],"hard":[28],"guarantee":[30],"both":[31],"quantity":[33],"and":[34,44,104,112,122],"quality":[35],"samples,":[38],"which":[39],"prohibits":[40],"practical":[42],"such":[47,117],"algorithms.":[48],"In":[49],"this":[50,136],"paper,":[51],"a":[52],"novel":[53],"RL":[54,91],"decision":[55,87],"optimization":[56],"method":[57,62,84,133],"proposed.":[59],"The":[60,128],"proposed":[61,110],"capable":[64],"reducing":[66],"dependence":[68],"on":[69],"via":[72],"incorporating":[73],"decision-making":[75,142],"evaluation":[76],"mechanism.":[77],"By":[78],"introducing":[79],"supervised":[80],"(SL),":[82],"our":[83],"optimizes":[85],"making":[88],"algorithm":[92],"by":[93],"using":[94],"demonstrations":[95],"or":[96],"samples.":[98],"Experiments":[99],"are":[100,151],"conducted":[101],"Pendulum":[103],"Puckworld":[105],"scenarios":[106],"test":[108],"method,":[111],"we":[113],"use":[114],"representative":[115],"as":[118,126],"deep":[119],"Q-network":[120],"(DQN)":[121],"Double":[123],"DQN":[124],"(DDQN)":[125],"benchmarks.":[127],"results":[129],"demonstrate":[130],"that":[131],"adopted":[134],"paper":[137],"can":[138],"effectively":[139],"agents":[145],"even":[146],"when":[147],"not":[152],"available.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}