{"id":"https://openalex.org/W2159131214","doi":"https://doi.org/10.1109/allerton.2012.6483246","title":"A novel Q-learning algorithm with function approximation for constrained Markov decision processes","display_name":"A novel Q-learning algorithm with function approximation for constrained Markov decision processes","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2159131214","doi":"https://doi.org/10.1109/allerton.2012.6483246","mag":"2159131214"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2012.6483246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2012.6483246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5025099834","display_name":"K. Lakshmanan","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"K. Lakshmanan","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038163398","display_name":"Shalabh Bhatnagar","orcid":"https://orcid.org/0000-0001-7644-3914"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shalabh Bhatnagar","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025099834"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.442,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.7445134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2","issue":null,"first_page":"400","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12288","display_name":"Optimization and Search Problems","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7402055263519287},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.7352612614631653},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5832415819168091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5512785911560059},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.532554030418396},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.510952889919281},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5044375658035278},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4877551198005676},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.486698180437088},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47007328271865845},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.4558895230293274},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.42886680364608765},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40100979804992676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3703766167163849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21308216452598572}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7402055263519287},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.7352612614631653},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5832415819168091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5512785911560059},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.532554030418396},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.510952889919281},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5044375658035278},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4877551198005676},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.486698180437088},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47007328271865845},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.4558895230293274},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.42886680364608765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40100979804992676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3703766167163849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21308216452598572},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/allerton.2012.6483246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2012.6483246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:46678","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1488584612","https://openalex.org/W1518931405","https://openalex.org/W1576580777","https://openalex.org/W1601081659","https://openalex.org/W1646707810","https://openalex.org/W2012117977","https://openalex.org/W2070570138","https://openalex.org/W2071983464","https://openalex.org/W2073314543","https://openalex.org/W2094387729","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2103198983","https://openalex.org/W2125852847","https://openalex.org/W2130304665","https://openalex.org/W2139418546","https://openalex.org/W2154204727","https://openalex.org/W2161270100","https://openalex.org/W2173945562","https://openalex.org/W2334782222","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4307347247","https://openalex.org/W6634483419"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W3105579180","https://openalex.org/W4287865573","https://openalex.org/W2134007003","https://openalex.org/W2019875157","https://openalex.org/W4310831616","https://openalex.org/W4301954754","https://openalex.org/W2105668821","https://openalex.org/W2025663273","https://openalex.org/W2951888513"],"abstract_inverted_index":{"We":[0,21,95],"present":[1],"a":[2,12,23,47,51,60,88,102,108],"novel":[3],"multi-timescale":[4],"Q-learning":[5,39,71],"algorithm":[6,35,81,113],"for":[7],"average":[8],"cost":[9],"control":[10],"in":[11,40,77,107],"Markov":[13],"decision":[14],"process":[15],"subject":[16],"to":[17,66,84,116,127],"multiple":[18],"inequality":[19,123],"constraints.":[20],"formulate":[22],"relaxed":[24],"version":[25],"of":[26,90,99,104,132],"this":[27],"problem":[28,103],"through":[29],"the":[30,67,91,97,121,133],"Lagrange":[31],"multiplier":[32],"method.":[33],"Our":[34,112],"is":[36,57,82,114],"different":[37],"from":[38],"that":[41],"it":[42],"updates":[43],"two":[44],"parameters":[45],"-":[46],"Q-value":[48,55],"parameter":[49,56],"and":[50,120],"policy":[52,68],"parameter.":[53,69],"The":[54],"updated":[58],"on":[59,101],"slower":[61],"time":[62],"scale":[63],"as":[64,87],"compared":[65],"Whereas":[70],"with":[72],"function":[73],"approximation":[74],"can":[75],"diverge":[76],"some":[78],"cases,":[79],"our":[80],"seen":[83,115,126],"be":[85,128],"convergent":[86],"result":[89],"aforementioned":[92],"timescale":[93],"separation.":[94],"show":[96],"results":[98],"experiments":[100],"constrained":[105],"routing":[106],"multistage":[109],"queueing":[110],"network.":[111],"exhibit":[117],"good":[118],"performance":[119],"various":[122],"constraints":[124],"are":[125],"satisfied":[129],"upon":[130],"convergence":[131],"algorithm.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}