{"id":"https://openalex.org/W2029593259","doi":"https://doi.org/10.1145/1842713.1842715","title":"A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm","display_name":"A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2029593259","doi":"https://doi.org/10.1145/1842713.1842715","mag":"2029593259"},"language":"en","primary_location":{"id":"doi:10.1145/1842713.1842715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1842713.1842715","pdf_url":null,"source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","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/A5011274206","display_name":"Sumit Kunnumkal","orcid":"https://orcid.org/0000-0002-6832-0508"},"institutions":[{"id":"https://openalex.org/I122328836","display_name":"Indian School of Business","ror":"https://ror.org/027t6ka17","country_code":"IN","type":"education","lineage":["https://openalex.org/I122328836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Kunnumkal","raw_affiliation_strings":["Indian School of Business, Gachibowli, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian School of Business, Gachibowli, Hyderabad","institution_ids":["https://openalex.org/I122328836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048544465","display_name":"H\u00fcseyin Topalo\u011flu","orcid":"https://orcid.org/0000-0002-3049-6719"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huseyin Topaloglu","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3193,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61062937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.998199999332428,"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":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.995199978351593,"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/monotone-polygon","display_name":"Monotone polygon","score":0.7373846173286438},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.6496126651763916},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6370391845703125},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6201387047767639},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5860109329223633},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5651463866233826},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5423643589019775},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.5097166895866394},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4985053539276123},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4934209883213043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.460943341255188},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4262278378009796},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4184474050998688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3747236728668213},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.368700236082077},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2816048860549927},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.20932301878929138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14864203333854675}],"concepts":[{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.7373846173286438},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.6496126651763916},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6370391845703125},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6201387047767639},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5860109329223633},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5651463866233826},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5423643589019775},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.5097166895866394},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4985053539276123},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4934209883213043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.460943341255188},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4262278378009796},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4184474050998688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3747236728668213},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.368700236082077},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2816048860549927},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.20932301878929138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14864203333854675},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1842713.1842715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1842713.1842715","pdf_url":null,"source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},{"id":"pmh:oai:eprints.exchange.isb.edu:57","is_oa":false,"landing_page_url":"https://eprints.exchange.isb.edu/id/eprint/57/1/sup_projection.pdf","pdf_url":"https://eprints.exchange.isb.edu/id/eprint/57/1/sup_projection.pdf","source":{"id":"https://openalex.org/S4377196660","display_name":"Digital Eprints Services at ISB (DESI) (Indian School of Business)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122328836","host_organization_name":"Indian School of Business","host_organization_lineage":["https://openalex.org/I122328836"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.7133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.7133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://legacy.orie.cornell.edu/huseyin/publications/sup_projection.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1346832739","display_name":null,"funder_award_id":"DMI-0422133CMMI-0758441","funder_id":"https://openalex.org/F4320337391","funder_display_name":"Division of Civil, Mechanical and Manufacturing Innovation"},{"id":"https://openalex.org/G3347798615","display_name":"Sensitivity Analysis of the Dynamic Fleet Management Problem with Applications in Fleet-Sizing, Pricing and Terminal Capacity Planning","funder_award_id":"0422133","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W100327610","https://openalex.org/W1499021337","https://openalex.org/W1515851193","https://openalex.org/W1568229137","https://openalex.org/W1576452626","https://openalex.org/W1583497301","https://openalex.org/W1601081659","https://openalex.org/W1745373831","https://openalex.org/W1854776945","https://openalex.org/W1969837807","https://openalex.org/W1990482617","https://openalex.org/W1995919276","https://openalex.org/W2009533501","https://openalex.org/W2017550604","https://openalex.org/W2022514640","https://openalex.org/W2054163426","https://openalex.org/W2069272564","https://openalex.org/W2102195169","https://openalex.org/W2118780114","https://openalex.org/W2119567691","https://openalex.org/W2124248187","https://openalex.org/W2125812768","https://openalex.org/W2137170340","https://openalex.org/W2139418546","https://openalex.org/W2142929170","https://openalex.org/W2147750403","https://openalex.org/W2152565894","https://openalex.org/W2171027013","https://openalex.org/W2235056388","https://openalex.org/W2248670831","https://openalex.org/W2322096602","https://openalex.org/W2334782222","https://openalex.org/W2487144912","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W2151661095","https://openalex.org/W2123424061"],"abstract_inverted_index":{"In":[0],"this":[1,17,84,127],"article,":[2],"we":[3,47,78,129],"develop":[4],"a":[5,11,42,54,146],"stochastic":[6,74,123],"approximation":[7,75,124,161],"method":[8,18,76,103],"to":[9,19,30,49,68,82,111,136,155],"solve":[10],"monotone":[12,35,43,141],"estimation":[13,44],"problem":[14,45],"and":[15],"use":[16],"enhance":[20],"the":[21,25,51,61,91,102,112,117,122,131,149,158,173,176,185,189],"empirical":[22],"performance":[23,174],"of":[24,53,63,93,101,121,148,175,188],"Q-learning":[26,132,150,177],"algorithm":[27,133,151,178],"when":[28,134],"applied":[29,135],"Markov":[31,137],"decision":[32,138],"problems":[33,139],"with":[34,95,109,140],"value":[36,142,159,190],"functions.":[37,143,191],"We":[38,58,115,144],"begin":[39],"by":[40,86,183],"considering":[41],"where":[46],"want":[48],"estimate":[50],"expectation":[52],"random":[55],"vector,":[56],"\u03b7.":[57],"assume":[59],"that":[60,77,105,152,157,172],"components":[62],"E":[64],"{\u03b7}":[65],"are":[66],"known":[67],"be":[69,180],"in":[70],"increasing":[71,96],"order.":[72],"The":[73,98],"propose":[79],"is":[80,104,166],"designed":[81],"exploit":[83],"information":[85],"projecting":[87],"its":[88],"iterates":[89],"onto":[90],"set":[92],"vectors":[94],"components.":[97],"novel":[99],"aspect":[100],"it":[106],"uses":[107,153],"projections":[108,154],"respect":[110],"max":[113],"norm.":[114],"show":[116],"almost":[118],"sure":[119],"convergence":[120],"method.":[125],"After":[126],"result,":[128],"consider":[130],"study":[145],"variant":[147],"ensure":[156],"function":[160],"obtained":[162],"at":[163],"each":[164],"iteration":[165],"also":[167],"monotone.":[168],"Computational":[169],"results":[170],"indicate":[171],"can":[179],"improved":[181],"significantly":[182],"exploiting":[184],"monotonicity":[186],"property":[187]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}