{"id":"https://openalex.org/W2889438065","doi":"https://doi.org/10.1587/transinf.2017edp7278","title":"Deep Reinforcement Learning with Sarsa and Q-Learning: A Hybrid Approach","display_name":"Deep Reinforcement Learning with Sarsa and Q-Learning: A Hybrid Approach","publication_year":2018,"publication_date":"2018-08-31","ids":{"openalex":"https://openalex.org/W2889438065","doi":"https://doi.org/10.1587/transinf.2017edp7278","mag":"2889438065"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edp7278","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7278","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7278/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7278/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072596372","display_name":"Zhixiong Xu","orcid":"https://orcid.org/0000-0003-0996-436X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-xiong XU","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078602454","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0002-6997-8504"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei CAO","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030992865","display_name":"Xiliang Chen","orcid":"https://orcid.org/0000-0001-5198-0932"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi-liang CHEN","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441349","display_name":"Chenxi Li","orcid":"https://orcid.org/0000-0002-7803-8282"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen-xi LI","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398081","display_name":"Yongliang Zhang","orcid":"https://orcid.org/0000-0002-8781-8504"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-liang ZHANG","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101900574","display_name":"Jun Lai","orcid":"https://orcid.org/0000-0002-3608-4985"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun LAI","raw_affiliation_strings":["Institute of Command Information System, PLA University of Science and Technology","Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Command Information System, PLA University of Science and Technology","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Information Sys-tem, PLA University of Science and Technology, Nanjing, 100190 China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1827,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84499775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"E101.D","issue":"9","first_page":"2315","last_page":"2322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9811999797821045,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8971120119094849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.881219744682312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519374251365662},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.52512127161026},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.45262783765792847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44881999492645264},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4420730769634247}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8971120119094849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.881219744682312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519374251365662},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.52512127161026},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.45262783765792847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44881999492645264},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4420730769634247}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edp7278","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7278","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7278/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2017edp7278","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7278","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7278/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889438065.pdf","grobid_xml":"https://content.openalex.org/works/W2889438065.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W166862392","https://openalex.org/W1522301498","https://openalex.org/W1553415142","https://openalex.org/W1557517019","https://openalex.org/W1595483645","https://openalex.org/W1600437712","https://openalex.org/W1757796397","https://openalex.org/W1980035368","https://openalex.org/W2021247827","https://openalex.org/W2047057213","https://openalex.org/W2096698697","https://openalex.org/W2100677568","https://openalex.org/W2112483970","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2513734981","https://openalex.org/W2535107243","https://openalex.org/W2552220135","https://openalex.org/W2588283865","https://openalex.org/W2746553466","https://openalex.org/W3041202696","https://openalex.org/W3103780890","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4239187508","https://openalex.org/W4240249953"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4319083788","https://openalex.org/W3047894882","https://openalex.org/W2968586400","https://openalex.org/W2942650110"],"abstract_inverted_index":{"The":[0,122],"commonly":[1],"used":[2],"Deep":[3,38,53,71,97],"Q":[4,41,54,72,98],"Networks":[5,42,55,73,99],"is":[6,84,107],"known":[7],"to":[8,22,51,74,88,96,132],"overestimate":[9],"action":[10],"values":[11],"under":[12],"certain":[13],"conditions.":[14],"It's":[15],"also":[16],"proved":[17],"that":[18,127],"overestimations":[19,102],"do":[20],"harm":[21],"performance,":[23],"which":[24,45],"might":[25],"cause":[26],"instability":[27],"and":[28,40,66,114,139],"divergence":[29],"of":[30,62,78],"learning.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,92],"present":[36],"the":[37,52,63,76,119,128],"Sarsa":[39,94],"(DSQN)":[43],"algorithm,":[44],"can":[46],"considered":[47],"as":[48],"an":[49],"enhancement":[50],"algorithm.":[56],"First,":[57],"DSQN":[58,105],"algorithm":[59,106],"takes":[60],"advantage":[61],"experience":[64],"replay":[65],"target":[67],"network":[68],"techniques":[69],"in":[70],"improve":[75],"stability":[77],"neural":[79],"networks.":[80],"Second,":[81],"double":[82],"estimator":[83],"utilized":[85],"for":[86,100],"Qlearning":[87],"reduce":[89],"overestimations.":[90],"Especially,":[91],"introduce":[93],"learning":[95,137],"removing":[101],"further.":[103],"Finally,":[104],"evaluated":[108],"on":[109],"cart-pole":[110],"balancing,":[111],"mountain":[112],"car":[113],"lunarlander":[115],"control":[116],"task":[117],"from":[118],"OpenAI":[120],"Gym.":[121],"empirical":[123],"evaluation":[124],"results":[125],"show":[126],"proposed":[129],"method":[130],"leads":[131],"reduced":[133],"overestimations,":[134],"more":[135],"stable":[136],"process":[138],"improved":[140],"performance.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
