{"id":"https://openalex.org/W2992629954","doi":"https://doi.org/10.1109/allerton.2019.8919665","title":"Reinforcement Learning for Optimal Control of Queueing Systems","display_name":"Reinforcement Learning for Optimal Control of Queueing Systems","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2992629954","doi":"https://doi.org/10.1109/allerton.2019.8919665","mag":"2992629954"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2019.8919665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th 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/A5042253177","display_name":"Bai Liu","orcid":"https://orcid.org/0000-0002-3950-4965"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bai Liu","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA","Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008882694","display_name":"Qiaomin Xie","orcid":"https://orcid.org/0000-0003-2834-6866"},"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":"Qiaomin Xie","raw_affiliation_strings":["Cornell University,School of Operations Research and Information Engineering,Ithaca,NY","School of Operations Research and Information Engineering, Cornell University, Ithaca, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of Operations Research and Information Engineering,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Operations Research and Information Engineering, Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036587377","display_name":"Eytan Modiano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eytan Modiano","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA","Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7893,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91507281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"663","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9991999864578247,"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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.9969000220298767,"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":0.9245027303695679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793129682540894},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.7045199871063232},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6690893173217773},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5845090746879578},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5783076882362366},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5132972598075867},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4900709390640259},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4748437702655792},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.449947714805603},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.43458572030067444},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41853049397468567},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38860785961151123},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.360848605632782},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.236200749874115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22131258249282837},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14247837662696838},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11506620049476624}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9245027303695679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793129682540894},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.7045199871063232},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6690893173217773},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5845090746879578},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5783076882362366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5132972598075867},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4900709390640259},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4748437702655792},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.449947714805603},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.43458572030067444},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41853049397468567},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38860785961151123},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.360848605632782},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.236200749874115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22131258249282837},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14247837662696838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11506620049476624},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2019.8919665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6100000143051147,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W9378068","https://openalex.org/W21934178","https://openalex.org/W32403112","https://openalex.org/W1530975313","https://openalex.org/W1597460884","https://openalex.org/W1845202788","https://openalex.org/W1850488217","https://openalex.org/W1973022038","https://openalex.org/W1995713768","https://openalex.org/W2004964364","https://openalex.org/W2020677283","https://openalex.org/W2041058815","https://openalex.org/W2042216697","https://openalex.org/W2093892790","https://openalex.org/W2098432798","https://openalex.org/W2103048107","https://openalex.org/W2103098926","https://openalex.org/W2104517640","https://openalex.org/W2111764152","https://openalex.org/W2120344179","https://openalex.org/W2135663206","https://openalex.org/W2155027007","https://openalex.org/W2157179371","https://openalex.org/W2168049152","https://openalex.org/W2168739325","https://openalex.org/W2293168792","https://openalex.org/W2333199285","https://openalex.org/W2510383364","https://openalex.org/W2565612488","https://openalex.org/W2612336410","https://openalex.org/W2768473197","https://openalex.org/W2963079995","https://openalex.org/W2963561337","https://openalex.org/W2963654220","https://openalex.org/W2971048633","https://openalex.org/W3020125231","https://openalex.org/W3151804457","https://openalex.org/W4299379543","https://openalex.org/W4300848284","https://openalex.org/W4301753813","https://openalex.org/W6639039794","https://openalex.org/W6676833704","https://openalex.org/W6683204974","https://openalex.org/W6733420677","https://openalex.org/W6745799698"],"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/W2807018115","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W4200250224"],"abstract_inverted_index":{"With":[0],"the":[1,15,56,66,83,92,98,110,115,145,151,167,185],"rapid":[2],"advance":[3],"of":[4,33,68,87,114,144],"information":[5,67],"technology,":[6],"network":[7,29,39,116],"systems":[8,64],"have":[9],"become":[10],"increasingly":[11],"complex":[12],"and":[13,177],"hence":[14],"underlying":[16,69],"system":[17],"dynamics":[18],"are":[19,52],"typically":[20],"unknown":[21],"or":[22,44],"difficult":[23],"to":[24,36,54,81,166],"characterize.":[25],"Finding":[26],"a":[27,125,141],"good":[28],"control":[30,58,85,117],"policy":[31,59,86],"is":[32,102],"significant":[34],"importance":[35],"achieving":[37],"desirable":[38],"performance":[40],"(e.g.,":[41],"high":[42],"throughput":[43],"low":[45],"average":[46,93,99,152,186],"job":[47,94],"delay).":[48],"Online/sequential":[49],"learning":[50,55,79],"algorithms":[51],"well-suited":[53],"optimal":[57,84,168],"from":[60],"observed":[61],"data":[62],"for":[63],"without":[65],"dynamics.":[70],"In":[71],"this":[72,121],"work,":[73],"we":[74,123],"consider":[75],"using":[76],"model-based":[77,137],"reinforcement":[78],"(RL)":[80],"learn":[82],"queueing":[88],"networks":[89],"so":[90],"that":[91,150,182],"delay":[95],"(or":[96],"equivalently":[97],"queue":[100,153,187],"backlog)":[101],"minimized.":[103],"Existing":[104],"RL":[105,138],"techniques,":[106],"however,":[107],"cannot":[108],"handle":[109],"unbounded":[111],"state":[112,146],"spaces":[113],"problem.":[118],"To":[119],"overcome":[120],"difficulty,":[122],"propose":[124],"new":[126],"algorithm,":[127],"called":[128],"Piecewise":[129],"Decaying":[130],"\u03b5-Greedy":[131],"Reinforcement":[132],"Learning":[133],"(PDGRL),":[134],"which":[135],"applies":[136],"methods":[139],"over":[140],"finite":[142],"subset":[143,161],"space.":[147],"We":[148,170],"establish":[149],"backlog":[154,188],"under":[155],"PDGRL":[156,172,183],"with":[157],"an":[158],"appropriately":[159],"constructed":[160],"can":[162],"be":[163],"arbitrarily":[164],"close":[165],"result.":[169],"evaluate":[171],"in":[173],"dynamic":[174],"server":[175],"allocation":[176],"routing":[178],"problems.":[179],"Simulations":[180],"show":[181],"minimizes":[184],"effectively.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}