{"id":"https://openalex.org/W2344944957","doi":"https://doi.org/10.5555/2946645.2946691","title":"Addressing environment non-stationarity by repeating Q-learning updates","display_name":"Addressing environment non-stationarity by repeating Q-learning updates","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2344944957","doi":"https://doi.org/10.5555/2946645.2946691","mag":"2344944957"},"language":"en","primary_location":{"id":"pmh:oai:cwi.nl:25117","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/25117","pdf_url":"https://ir.cwi.nl/pub/25117/p1582-abdallah.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research vol. 17","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/25117/p1582-abdallah.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015381412","display_name":"Sherief Abdallah","orcid":"https://orcid.org/0000-0002-1213-2014","observed_orcids":["https://orcid.org/0000-0002-1213-2014"]},"institutions":[{"id":"https://openalex.org/I193260172","display_name":"British University in Dubai","ror":"https://ror.org/00mc18523","country_code":"AE","type":"education","lineage":["https://openalex.org/I193260172"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sherief Abdallah","raw_affiliation_strings":["The British University in Dubai , Dubai, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-1213-2014","affiliations":[{"raw_affiliation_string":"The British University in Dubai , Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I193260172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069752991","display_name":"Michael Kaisers","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]},{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Kaisers","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, The Netherlands and Maastricht University, The Netherlands#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, The Netherlands and Maastricht University, The Netherlands#TAB#","institution_ids":["https://openalex.org/I1341640284","https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0921,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.92225727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"1582","last_page":"1612"},"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/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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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/q-learning","display_name":"Q-learning","score":0.9869999885559082},{"id":"https://openalex.org/keywords/non-stationary-environments","display_name":"non-stationary environments","score":0.9599999785423279},{"id":"https://openalex.org/keywords/noisy-environments","display_name":"noisy environments","score":0.6209999918937683},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.5659999847412109},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8709999918937683},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7960000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931833863258362},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7811340093612671},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7519654035568237},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7209137082099915},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.5929356813430786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869346857070923},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.5798727869987488},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5663284063339233},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4953235685825348},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.45000413060188293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43721985816955566},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.431417852640152},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42987340688705444},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37598925828933716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3215565085411072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1507951319217682},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:cwi.nl:25117","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/25117","pdf_url":"https://ir.cwi.nl/pub/25117/p1582-abdallah.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research vol. 17","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:cwi:oai:cwi.nl:25117","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/25117","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research, 17","raw_type":"info:eu-repo/semantics/article"},{"id":"mag:2344944957","doi":null,"is_oa":false,"landing_page_url":"https://jmlr.org/papers/volume17/14-037/14-037.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},{"id":"mag:3014176776","doi":"https://doi.org/10.5555/2946645.2946691","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2946645.2946691","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":{"id":"pmh:oai:cwi.nl:25117","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/25117","pdf_url":"https://ir.cwi.nl/pub/25117/p1582-abdallah.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research vol. 17","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310569","display_name":"British University in Dubai","ror":"https://ror.org/00mc18523"},{"id":"https://openalex.org/F4320323517","display_name":"Emirates Foundation","ror":"https://ror.org/05nd26619"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2344944957.pdf","grobid_xml":"https://content.openalex.org/works/W2344944957.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W1491843047","https://openalex.org/W1495863347","https://openalex.org/W1500331901","https://openalex.org/W1515303567","https://openalex.org/W1515851193","https://openalex.org/W1540725368","https://openalex.org/W1552540037","https://openalex.org/W1605188341","https://openalex.org/W1705315349","https://openalex.org/W1850488217","https://openalex.org/W1944301273","https://openalex.org/W1967250398","https://openalex.org/W1998498767","https://openalex.org/W2021563785","https://openalex.org/W2031098375","https://openalex.org/W2042708996","https://openalex.org/W2053616263","https://openalex.org/W2087322096","https://openalex.org/W2097498347","https://openalex.org/W2103048296","https://openalex.org/W2103437045","https://openalex.org/W2104602264","https://openalex.org/W2105643086","https://openalex.org/W2115211925","https://openalex.org/W2115524942","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2123447947","https://openalex.org/W2123890518","https://openalex.org/W2138362680","https://openalex.org/W2146917784","https://openalex.org/W2148825261","https://openalex.org/W2152835608","https://openalex.org/W2154806059","https://openalex.org/W2156060009","https://openalex.org/W2156211713","https://openalex.org/W2157016390","https://openalex.org/W2158596240","https://openalex.org/W2163533082","https://openalex.org/W2180541313","https://openalex.org/W2293385286","https://openalex.org/W2312609093","https://openalex.org/W7124140802","https://openalex.org/W7124214921"],"related_works":["https://openalex.org/W1495863347","https://openalex.org/W1550943870","https://openalex.org/W7058411463","https://openalex.org/W3125946732","https://openalex.org/W4313165221","https://openalex.org/W7005531169","https://openalex.org/W3186628802","https://openalex.org/W4396891890","https://openalex.org/W7096968147","https://openalex.org/W7162645050"],"abstract_inverted_index":{"Q-learning":[0,76,87],"(QL)":[1],"is":[2,9,49],"a":[3,50,78],"popular":[4],"reinforcement":[5],"learning":[6,55,79,130],"algorithm":[7,80],"that":[8,43,81,109],"guaranteed":[10],"to":[11,13],"converge":[12],"optimal":[14],"policies":[15],"in":[16,25,67,117,150],"Markov":[17],"decision":[18],"processes.":[19],"However,":[20],"QL":[21,116,144],"exhibits":[22],"an":[23,35],"artifact:":[24],"expectation,":[26],"the":[27,32,39,54,83,93,101,112,122,125,129,135,146],"effective":[28],"rate":[29],"of":[30,34,41,86,115],"updating":[31],"value":[33],"action":[36],"depends":[37],"on":[38],"probability":[40],"choosing":[42],"action.":[44],"In":[45],"other":[46],"words,":[47],"there":[48],"tight":[51],"coupling":[52,62,123],"between":[53,97,124],"dynamics":[56],"and":[57,95,100,128,138,145,157],"underlying":[58],"execution":[59,126],"policy.":[60],"This":[61],"can":[63],"cause":[64],"performance":[65],"degradation":[66],"noisy":[68,151],"non-stationary":[69,152],"environments.":[70,153],"Here,":[71],"we":[72],"introduce":[73],"Repeated":[74],"Update":[75],"(RUQL),":[77],"resolves":[82],"undesirable":[84],"artifact":[85],"while":[88,120],"maintaining":[89],"simplicity.":[90],"We":[91],"analyze":[92],"similarities":[94],"differences":[96],"RUQL,":[98],"QL,":[99],"closest":[102,147],"state-of-the-art":[103,148],"algorithms":[104,149],"theoretically.":[105],"Our":[106],"analysis":[107],"shows":[108],"RUQL":[110,141],"maintains":[111],"convergence":[113],"guarantee":[114],"stationary":[118],"environments,":[119],"relaxing":[121],"policy":[127],"dynamics.":[131],"Experimental":[132],"results":[133],"confirm":[134],"theoretical":[136],"insights":[137],"show":[139],"how":[140],"outperforms":[142],"both":[143],"\u00a92016":[154],"Sherief":[155],"Abdallah":[156],"Michael":[158],"Kaisers.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}