{"id":"https://openalex.org/W1982262386","doi":"https://doi.org/10.1109/tsmcc.2011.2106494","title":"Experience Replay for Real-Time Reinforcement Learning Control","display_name":"Experience Replay for Real-Time Reinforcement Learning Control","publication_year":2011,"publication_date":"2011-02-24","ids":{"openalex":"https://openalex.org/W1982262386","doi":"https://doi.org/10.1109/tsmcc.2011.2106494","mag":"1982262386"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcc.2011.2106494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcc.2011.2106494","pdf_url":null,"source":{"id":"https://openalex.org/S4210227557","display_name":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)","issn_l":"1094-6977","issn":["1094-6977","1558-2442"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)","raw_type":"journal-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/A5026485727","display_name":"S Charles Adam","orcid":null},"institutions":[{"id":"https://openalex.org/I96120398","display_name":"De Nederlandsche Bank","ror":"https://ror.org/02fabx761","country_code":"NL","type":"funder","lineage":["https://openalex.org/I96120398"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sander Adam","raw_affiliation_strings":["Large Corporates andMerchant Banking Division, ABN AMRO Bank, Amsterdam, Netherlands","Large Corporates & Merchant Banking Div., ABN AMRO Bank, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Corporates andMerchant Banking Division, ABN AMRO Bank, Amsterdam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Large Corporates & Merchant Banking Div., ABN AMRO Bank, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I96120398"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center for Systems and Control, Technical University Delft, Delft, Netherlands","Delft Center for Syst. & Control, Tech. Univ. Delft, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Technical University Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Syst. & Control, Tech. Univ. Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control, Technical University Delft, Delft, Netherlands","Delft Center for Syst. & Control, Tech. Univ. Delft, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Technical University Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Syst. & Control, Tech. Univ. Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7005,"has_fulltext":false,"cited_by_count":263,"citation_normalized_percentile":{"value":0.97233336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"42","issue":"2","first_page":"201","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908000230789185,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908000230789185,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8934858441352844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720808982849121},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5809611082077026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5264689922332764},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4814995527267456},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45414212346076965},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4013195335865021}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8934858441352844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720808982849121},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5809611082077026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264689922332764},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4814995527267456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45414212346076965},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4013195335865021},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmcc.2011.2106494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcc.2011.2106494","pdf_url":null,"source":{"id":"https://openalex.org/S4210227557","display_name":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)","issn_l":"1094-6977","issn":["1094-6977","1558-2442"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W166587241","https://openalex.org/W1491843047","https://openalex.org/W1529558080","https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1585546346","https://openalex.org/W1626155273","https://openalex.org/W1646707810","https://openalex.org/W1758031947","https://openalex.org/W1986944783","https://openalex.org/W2048226872","https://openalex.org/W2084202551","https://openalex.org/W2087767021","https://openalex.org/W2089434629","https://openalex.org/W2098432798","https://openalex.org/W2104641222","https://openalex.org/W2105336508","https://openalex.org/W2107977784","https://openalex.org/W2113913482","https://openalex.org/W2114882146","https://openalex.org/W2115192345","https://openalex.org/W2119870041","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2125510930","https://openalex.org/W2125612430","https://openalex.org/W2135721773","https://openalex.org/W2141559645","https://openalex.org/W2150923691","https://openalex.org/W2151661095","https://openalex.org/W2160308170","https://openalex.org/W2164147167","https://openalex.org/W2165131254","https://openalex.org/W2266260776","https://openalex.org/W2305205647","https://openalex.org/W2305373430","https://openalex.org/W2309004380","https://openalex.org/W2586680856","https://openalex.org/W2999905431","https://openalex.org/W3139377883","https://openalex.org/W4205326910","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4285719527","https://openalex.org/W6635147684","https://openalex.org/W6638058698","https://openalex.org/W6672797807","https://openalex.org/W6677737365","https://openalex.org/W6682443896","https://openalex.org/W6683472505"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2350715914","https://openalex.org/W2120821724","https://openalex.org/W2379529020","https://openalex.org/W2101175215","https://openalex.org/W2893549521","https://openalex.org/W2330311678","https://openalex.org/W2352322616","https://openalex.org/W2574438335"],"abstract_inverted_index":{"Reinforcement-learning":[0],"(RL)":[1],"algorithms":[2],"can":[3,115],"automatically":[4],"learn":[5],"optimal":[6],"control":[7,19,76,87],"strategies":[8],"for":[9,17,128,147],"nonlinear,":[10],"possibly":[11],"stochastic":[12],"systems.":[13,65],"A":[14],"promising":[15],"approach":[16],"RL":[18,41,47,73,122,152],"is":[20],"experience":[21],"replay":[22],"(ER),":[23],"which":[24],"learns":[25],"quickly":[26],"from":[27],"a":[28,80,89,106,110],"limited":[29],"amount":[30],"of":[31,88,150],"data,":[32],"by":[33,97],"repeatedly":[34],"presenting":[35],"these":[36],"data":[37],"to":[38,63],"an":[39],"underlying":[40],"algorithm.":[42],"Despite":[43],"its":[44,57],"benefits,":[45],"ER":[46,72,112,151],"has":[48],"been":[49,61],"studied":[50],"only":[51],"sporadically":[52],"in":[53,67,153],"the":[54,85,129,148],"literature,":[55],"and":[56,84,100,124,132],"applications":[58],"have":[59],"largely":[60],"confined":[62],"simulated":[64],"Therefore,":[66],"this":[68,126],"paper,":[69],"we":[70,108],"evaluate":[71],"on":[74],"real-time":[75,93,137],"experiments":[77,94],"that":[78,114,140],"involve":[79],"pendulum":[81],"swing-up":[82],"problem":[83],"vision-based":[86],"goalkeeper":[90],"robot.":[91],"These":[92],"are":[95,141,144],"complemented":[96],"simulation":[98],"studies":[99],"comparisons":[101],"with":[102,118],"traditional":[103],"RL.":[104],"As":[105],"preliminary,":[107],"develop":[109],"general":[111],"framework":[113,127],"be":[116],"combined":[117],"essentially":[119],"any":[120],"incremental":[121],"technique,":[123],"instantiate":[125],"approximate":[130],"Q-learning":[131],"SARSA":[133],"algorithms.":[134],"The":[135],"successful":[136],"learning":[138],"results":[139],"presented":[142],"here":[143],"highly":[145],"encouraging":[146],"applicability":[149],"practice.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}