{"id":"https://openalex.org/W2588283865","doi":"https://doi.org/10.1109/ssci.2016.7849837","title":"Deep reinforcement learning with experience replay based on SARSA","display_name":"Deep reinforcement learning with experience replay based on SARSA","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2588283865","doi":"https://doi.org/10.1109/ssci.2016.7849837","mag":"2588283865"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2016.7849837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7849837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457223","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0002-4570-8753"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787656","display_name":"Kun Shao","orcid":"https://orcid.org/0000-0003-0965-4302"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Shao","raw_affiliation_strings":["Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100624298"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":9.3119,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":{"value":0.97959645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9857000112533569,"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":0.9746000170707703,"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":0.8914638757705688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802348256111145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7646445631980896},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7475317120552063},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5639172196388245},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5370646119117737},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5146404504776001},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46386876702308655},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.46358558535575867},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43591418862342834},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41643646359443665}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8914638757705688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802348256111145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7646445631980896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7475317120552063},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5639172196388245},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5370646119117737},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5146404504776001},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46386876702308655},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.46358558535575867},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43591418862342834},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41643646359443665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci.2016.7849837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7849837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W13846533","https://openalex.org/W124173549","https://openalex.org/W1515851193","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1813260711","https://openalex.org/W2031692836","https://openalex.org/W2050838777","https://openalex.org/W2052688942","https://openalex.org/W2112796928","https://openalex.org/W2143884379","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2154997814","https://openalex.org/W2257979135","https://openalex.org/W2290874868","https://openalex.org/W2312998612","https://openalex.org/W2342744201","https://openalex.org/W2489401300","https://openalex.org/W2919115771","https://openalex.org/W3103780890","https://openalex.org/W4298857966","https://openalex.org/W6635465357","https://openalex.org/W6696866154"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W1966456942","https://openalex.org/W2166117066","https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3127551068","https://openalex.org/W2808546214","https://openalex.org/W2152445738","https://openalex.org/W225045806"],"abstract_inverted_index":{"SARSA,":[0],"as":[1,77],"one":[2],"kind":[3],"of":[4],"on-policy":[5],"reinforcement":[6,63],"learning":[7,13,37,55,64,95],"methods,":[8],"is":[9,44,69],"integrated":[10],"with":[11],"deep":[12,26,62,67,93,103],"to":[14,30,38,46,52,71,80],"solve":[15,72],"the":[16,32,48,85,92],"video":[17,82],"games":[18],"control":[19,74],"problems":[20,75],"in":[21,99],"this":[22,58],"paper.":[23],"We":[24],"use":[25],"convolutional":[27],"neural":[28],"network":[29],"estimate":[31],"state-action":[33],"value,":[34],"and":[35],"SARSA":[36,68,94],"update":[39],"it.":[40],"Besides,":[41],"experience":[42],"replay":[43],"introduced":[45],"make":[47],"training":[49],"process":[50],"suitable":[51],"scalable":[53],"machine":[54],"problems.":[56],"In":[57],"way,":[59],"a":[60],"new":[61],"method,":[65],"called":[66],"proposed":[70],"complicated":[73],"such":[76],"imitating":[78],"human":[79],"play":[81],"games.":[83],"From":[84],"experiments":[86],"results,":[87],"we":[88],"can":[89],"conclude":[90],"that":[91],"shows":[96],"better":[97],"performances":[98],"some":[100],"aspects":[101],"than":[102],"Q":[104],"learning.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}