{"id":"https://openalex.org/W2913130183","doi":"https://doi.org/10.1109/ssci.2018.8628889","title":"Switching Deep Reinforcement Learning based Intelligent Online Decision Making for Autonomous Systems under Uncertain Environment","display_name":"Switching Deep Reinforcement Learning based Intelligent Online Decision Making for Autonomous Systems under Uncertain Environment","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913130183","doi":"https://doi.org/10.1109/ssci.2018.8628889","mag":"2913130183"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2018.8628889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2018.8628889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-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/A5088809666","display_name":"Zejian Zhou","orcid":"https://orcid.org/0000-0002-0252-6765"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zejian Zhou","raw_affiliation_strings":["Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100717012","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0003-4130-7925"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":0.5069,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75499588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"1453","last_page":"1460"},"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/T12761","display_name":"Data Stream Mining Techniques","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8915799856185913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7391058802604675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6403591632843018},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5182373523712158},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5165464282035828},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48373129963874817},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.45291706919670105},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4403705596923828},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.43987706303596497}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8915799856185913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391058802604675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403591632843018},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5182373523712158},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5165464282035828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48373129963874817},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.45291706919670105},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4403705596923828},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43987706303596497},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci.2018.8628889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2018.8628889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W60519195","https://openalex.org/W778742492","https://openalex.org/W1515851193","https://openalex.org/W1757796397","https://openalex.org/W1796544916","https://openalex.org/W2031727428","https://openalex.org/W2056584142","https://openalex.org/W2084970142","https://openalex.org/W2103496339","https://openalex.org/W2109910161","https://openalex.org/W2115524942","https://openalex.org/W2132514348","https://openalex.org/W2152670157","https://openalex.org/W2168342951","https://openalex.org/W2577420768","https://openalex.org/W2962872206","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6742380005","https://openalex.org/W6821401181"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4306904969","https://openalex.org/W4366700029","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W4285230481","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176"],"abstract_inverted_index":{"In":[0],"this":[1,41,82],"paper,":[2,83],"finite":[3],"horizon":[4],"intelligent":[5],"decision":[6,33],"making":[7,34],"problem":[8],"has":[9,49],"been":[10,50],"investigated":[11],"for":[12,36,77],"autonomous":[13,37,152],"systems":[14],"especially":[15,35],"under":[16,92],"uncertain":[17],"environment.":[18,107],"According":[19],"to":[20,70,104,134,159,169],"latest":[21],"studies,":[22],"the":[23,30,68,106,109,123,135,141,148,151,156,171,174],"uncertainty":[24],"of":[25,32,63,86,114,173],"environment":[26,149],"will":[27,117,154],"seriously":[28],"affect":[29],"effectiveness":[31,172],"systems.":[38],"To":[39],"handle":[40],"issues,":[42],"transfer":[43],"learning":[44,48,127,132],"and":[45,74,120],"deep":[46,125],"reinforcement":[47,126],"presented":[51],"recently.":[52],"However,":[53],"those":[54],"existing":[55],"Learning":[56],"algorithms":[57],"commonly":[58],"needs":[59],"a":[60,84,99,112],"large":[61],"set":[62],"state":[64],"space":[65],"which":[66,128],"cause":[67],"algorithm":[69],"be":[71,118],"time":[72],"consuming":[73],"not":[75],"suitable":[76],"real-time":[78],"application.":[79],"Therefore,":[80],"in":[81],"library":[85],"polices":[87],"trained":[88],"using":[89],"Deep":[90],"Q-Learning":[91],"similar":[93],"environments":[94],"are":[95,167],"built":[96],"firstly.":[97],"Then,":[98],"neural":[100],"network":[101],"is":[102],"designed":[103,124,175],"estimate":[105],"Using":[108],"learned":[110],"environment,":[111],"novel":[113,142],"switching":[115],"policy":[116,143,158],"developed":[119],"integrated":[121],"with":[122],"can":[129],"efficiently":[130],"stop":[131],"according":[133],"practical":[136],"error":[137],"tolerance.":[138],"Meanwhile,":[139],"through":[140],"evaluation":[144],"method":[145],"based":[146],"on":[147],"estimator,":[150],"agent":[153],"select":[155],"best":[157],"followin":[160],"an":[161],"online":[162],"manner.":[163],"Eventually,":[164],"simulation":[165],"results":[166],"provided":[168],"demonstrate":[170],"algorithm.":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}