{"id":"https://openalex.org/W3202404030","doi":"https://doi.org/10.1155/2021/5370281","title":"Minibatch Recursive Least Squares Q\u2010Learning","display_name":"Minibatch Recursive Least Squares Q\u2010Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3202404030","doi":"https://doi.org/10.1155/2021/5370281","mag":"3202404030","pmid":"https://pubmed.ncbi.nlm.nih.gov/34659393","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/8519689"},"language":"en","primary_location":{"id":"doi:10.1155/2021/5370281","doi":"https://doi.org/10.1155/2021/5370281","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5370281","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5370281.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W3202404030"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/cin/2021/5370281.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100710937","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-2785-0510","observed_orcids":["https://orcid.org/0000-0002-2785-0510"]},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China"],"raw_orcid":"https://orcid.org/0000-0002-2785-0510","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056534182","display_name":"Song Qi","orcid":"https://orcid.org/0000-0002-9748-5942","observed_orcids":["https://orcid.org/0000-0002-9748-5942"]},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102491745","display_name":"Meng Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng Meng","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, Hainan 570228, China","institution_ids":["https://openalex.org/I20942203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100710937"],"corresponding_institution_ids":["https://openalex.org/I20942203"],"apc_list":{"value":2550,"currency":"USD","value_usd":2550},"apc_paid":{"value":2550,"currency":"USD","value_usd":2550},"fwci":0.0725,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33601833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"2021","issue":"1","first_page":"5370281","last_page":"5370281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7480000257492065},{"id":"https://openalex.org/keywords/recursive-least-squares","display_name":"recursive least squares","score":0.8849999904632568},{"id":"https://openalex.org/keywords/linear-function-approximation","display_name":"linear function approximation","score":0.8080000281333923},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.9350000023841858},{"id":"https://openalex.org/keywords/experience-replay","display_name":"experience replay","score":0.8339999914169312},{"id":"https://openalex.org/keywords/convergence","display_name":"convergence","score":0.3479999899864197},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.6190000176429749},{"id":"https://openalex.org/keywords/cartpole","display_name":"CartPole","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497353553771973},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7019872665405273},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6967040300369263},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6965432167053223},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5857559442520142},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5578676462173462},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.531245231628418},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4853626489639282},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4651898443698883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42424148321151733},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41868507862091064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3764446973800659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3203933835029602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2442522644996643},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21345660090446472},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1155/2021/5370281","doi":"https://doi.org/10.1155/2021/5370281","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5370281","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5370281.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},{"id":"pmid:34659393","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34659393","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational intelligence and neuroscience","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8519689","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC8519689/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Comput Intell Neurosci","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2021/5370281","doi":"https://doi.org/10.1155/2021/5370281","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5370281","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5370281.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4153670792","display_name":"\u8fde\u7eed\u52a8\u4f5c\u7a7a\u95f4\u6df1\u5ea6Actor-Critic\u7b97\u6cd5\u7814\u7a76","funder_award_id":"61762032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7963907384","display_name":"\u57fa\u4e8e\u795e\u7ecf\u52a8\u529b\u7cfb\u7edf\u7684\u975e\u5149\u6ed1\u4f18\u5316\u65b9\u6cd5\u7814\u7a76","funder_award_id":"11961018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202404030.pdf","grobid_xml":"https://content.openalex.org/works/W3202404030.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W2078394884","https://openalex.org/W2101234009","https://openalex.org/W2111072639","https://openalex.org/W2120346334","https://openalex.org/W2121092017","https://openalex.org/W2141583550","https://openalex.org/W2145339207","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2260756217","https://openalex.org/W2586680856","https://openalex.org/W2724169821","https://openalex.org/W2738226240","https://openalex.org/W2746553466","https://openalex.org/W2752236613","https://openalex.org/W2781726626","https://openalex.org/W2785998395","https://openalex.org/W2808139065","https://openalex.org/W2953364219","https://openalex.org/W2963472011","https://openalex.org/W2964547635","https://openalex.org/W3014047796","https://openalex.org/W3088286182","https://openalex.org/W3115148317","https://openalex.org/W3148454182","https://openalex.org/W3170834283","https://openalex.org/W3171878853","https://openalex.org/W3173419186","https://openalex.org/W4242606736","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2963472011","https://openalex.org/W1161019634","https://openalex.org/W4386514919","https://openalex.org/W4416078036","https://openalex.org/W4416374779","https://openalex.org/W2549225575","https://openalex.org/W7214828265","https://openalex.org/W2885746304","https://openalex.org/W2348126519","https://openalex.org/W2907626093"],"abstract_inverted_index":{"The":[0],"deep":[1],"Q-network":[2],"(DQN)":[3],"is":[4,202],"one":[5,123,127],"of":[6,49,66,69,112,119,212,219,233],"the":[7,26,47,67,89,98,106,133,137,143,148,153,174,210,217,222,231],"most":[8],"successful":[9],"reinforcement":[10,28],"learning":[11,29,107],"algorithms,":[12],"but":[13,61],"it":[14,158,194,201],"has":[15],"some":[16],"drawbacks":[17],"such":[18],"as":[19,152,173,180],"slow":[20],"convergence":[21,38,198],"and":[22,39,109,126,136,141,166,225,229],"instability.":[23],"In":[24,51,75,182],"contrast,":[25],"traditional":[27,70,99],"algorithms":[30,71],"with":[31,84,102,121,207],"linear":[32,85,103,128],"function":[33,86,104],"approximation":[34],"usually":[35],"have":[36,58],"faster":[37],"better":[40,197],"stability,":[41],"although":[42],"they":[43,62],"easily":[44],"suffer":[45],"from":[46,97],"curse":[48],"dimensionality.":[50],"recent":[52],"years,":[53],"many":[54],"improvements":[55],"to":[56,72,117],"DQN":[57,172],"been":[59],"made,":[60],"seldom":[63],"make":[64],"use":[65],"advantage":[68],"improve":[73],"DQN.":[74,208],"this":[76,213],"paper,":[77,214],"we":[78,215],"propose":[79],"a":[80,156],"novel":[81],"Q-learning":[82,94,100],"algorithm":[83,101],"approximation,":[87,105],"called":[88],"minibatch":[90,138],"recursive":[91],"least":[92],"squares":[93],"(MRLS-Q).":[95],"Different":[96],"mechanism":[108],"model":[110],"structure":[111],"MRLS-Q":[113,184,220],"are":[114],"more":[115],"similar":[116],"those":[118],"DQNs":[120],"only":[122],"input":[124],"layer":[125,176],"output":[129],"layer.":[130],"It":[131],"uses":[132,142,185],"experience":[134],"replay":[135],"training":[139],"mode":[140],"agent's":[144,149],"states":[145],"rather":[146],"than":[147],"state-action":[150],"pairs":[151],"inputs.":[154],"As":[155],"result,":[157],"can":[159,167,195],"be":[160,168],"used":[161,203],"alone":[162,204],"for":[163,177],"low-dimensional":[164],"problems":[165,179],"seamlessly":[169],"integrated":[170,206],"into":[171],"last":[175],"high-dimensional":[178],"well.":[181],"addition,":[183],"our":[186],"proposed":[187],"average":[188],"RLS":[189],"optimization":[190],"technique,":[191],"so":[192],"that":[193],"achieve":[196],"performance":[199],"whether":[200],"or":[205],"At":[209],"end":[211],"demonstrate":[216],"effectiveness":[218],"on":[221],"CartPole":[223],"problem":[224],"four":[226],"Atari":[227],"games":[228],"investigate":[230],"influences":[232],"its":[234],"hyperparameters":[235],"experimentally.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2021-10-11T00:00:00"}