{"id":"https://openalex.org/W3139043417","doi":"https://doi.org/10.1109/bigdata50022.2020.9377951","title":"State Action Separable Reinforcement Learning","display_name":"State Action Separable Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3139043417","doi":"https://doi.org/10.1109/bigdata50022.2020.9377951","mag":"3139043417"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/A5102004044","display_name":"Ziyao Zhang","orcid":"https://orcid.org/0000-0002-0617-1340"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ziyao Zhang","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733565","display_name":"Liang Ma","orcid":"https://orcid.org/0000-0002-4366-0784"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Ma","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, United States","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917506","display_name":"Kin K. Leung","orcid":"https://orcid.org/0000-0002-3860-6257"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kin K. Leung","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046120615","display_name":"Konstantinos Poularakis","orcid":"https://orcid.org/0000-0003-2570-3813"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Poularakis","raw_affiliation_strings":["Yale University, New Haven, CT, United States"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, United States","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072108555","display_name":"Mudhakar Srivatsa","orcid":"https://orcid.org/0000-0002-5874-3750"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mudhakar Srivatsa","raw_affiliation_strings":["Yale University, New Haven, CT, United States"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, United States","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102004044"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58489266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"8","issue":null,"first_page":"123","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9782000184059143,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.947700023651123,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8987312912940979},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.769183874130249},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6619597673416138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6313284039497375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5936700105667114},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5520343780517578},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5364314913749695},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5069220662117004},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.478588342666626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46642810106277466},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46059051156044006},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46045640110969543},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45642679929733276},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45316967368125916},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38536471128463745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2535398006439209},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23880094289779663},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11524400115013123}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8987312912940979},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.769183874130249},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6619597673416138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313284039497375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936700105667114},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5520343780517578},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5364314913749695},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5069220662117004},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.478588342666626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46642810106277466},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46059051156044006},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46045640110969543},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45642679929733276},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45316967368125916},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38536471128463745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2535398006439209},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23880094289779663},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11524400115013123},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W298976786","https://openalex.org/W1515851193","https://openalex.org/W1757796397","https://openalex.org/W1825077972","https://openalex.org/W1977177161","https://openalex.org/W2072128103","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150147323","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2799245749","https://openalex.org/W2950403652","https://openalex.org/W2950872548","https://openalex.org/W2953334758","https://openalex.org/W2963097726","https://openalex.org/W2963375351","https://openalex.org/W2963488340","https://openalex.org/W2963864421","https://openalex.org/W2964158321","https://openalex.org/W2964220198","https://openalex.org/W2971631853","https://openalex.org/W3007324819","https://openalex.org/W3008295237","https://openalex.org/W3037435714","https://openalex.org/W4231109964","https://openalex.org/W4288614963","https://openalex.org/W4297789121","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6610666704","https://openalex.org/W6637967152","https://openalex.org/W6638473186","https://openalex.org/W6682198394","https://openalex.org/W6683001934","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6729556111","https://openalex.org/W6740836278","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6750453880","https://openalex.org/W6759315145","https://openalex.org/W6763849353","https://openalex.org/W6767787902","https://openalex.org/W6774646964"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W3105579180","https://openalex.org/W2807018115","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Reinforcement":[0,117],"Learning":[1,118],"(RL)":[2],"based":[3],"methods":[4],"have":[5],"seen":[6],"their":[7],"paramount":[8],"successes":[9],"in":[10,17,53,64,96,187],"solving":[11],"serial":[12],"decision-making":[13],"and":[14,28,38,191],"control":[15],"problems":[16,82],"recent":[18],"years.":[19],"For":[20],"conventional":[21],"RL":[22,208],"formulations,":[23],"Markov":[24],"Decision":[25],"Process":[26],"(MDP)":[27],"state-action-value":[29,68],"function":[30,129,186],"are":[31],"the":[32,35,51,67,77,83,93,98,121,127,145,149,153,165,179,184,188],"basis":[33],"for":[34,80,132,182],"problem":[36],"modeling":[37],"policy":[39],"evaluation.":[40],"However,":[41],"several":[42,199],"challenging":[43],"issues":[44],"still":[45],"remain.":[46],"Among":[47],"most":[48],"cited":[49],"issues,":[50],"inefficiency":[52],"utilizing":[54],"training":[55],"data":[56],"is":[57,124,141,170,178,193],"an":[58],"important":[59],"factor":[60],"that":[61,72,151,161,203],"causes":[62],"difficulties":[63],"accurately":[65],"approximating":[66],"function.":[69],"We":[70],"observe":[71],"although":[73],"actions":[74],"directly":[75],"define":[76],"agents'":[78],"behaviors,":[79],"many":[81],"next":[84],"state":[85,88,103,155],"after":[86],"a":[87,102,110,137,194],"transition":[89,139],"matters":[90],"more":[91],"than":[92],"action":[94,122,150],"taken,":[95],"determining":[97],"return":[99],"of":[100,168],"such":[101],"transition.":[104,156],"In":[105],"this":[106],"regard,":[107],"we":[108],"propose":[109],"new":[111],"learning":[112,130,134],"paradigm,":[113],"State":[114],"Action":[115],"Separable":[116],"(sasRL),":[119],"wherein":[120],"space":[123],"decoupled":[125],"from":[126],"value":[128,185],"process":[131],"higher":[133],"efficiency.":[135],"Then,":[136],"light-weight":[138],"model":[140],"learned":[142],"to":[143,147,212],"assist":[144],"agent":[146],"determine":[148],"triggers":[152],"associated":[154],"Our":[157],"convergence":[158,166,180],"analysis":[159],"reveals":[160],"under":[162],"certain":[163],"conditions,":[164],"time":[167,181],"sasRL":[169,204],"O(T":[171],"<sup":[172],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1/k</sup>":[174],"),":[175],"where":[176],"T":[177],"updating":[183],"MDP-based":[189,207],"formulation":[190],"k":[192],"weighting":[195],"factor.":[196],"Experiments":[197],"on":[198],"gaming":[200],"scenarios":[201],"show":[202],"outperforms":[205],"state-of-the-art":[206],"algorithms":[209],"by":[210],"up":[211],"75%.":[213]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}