{"id":"https://openalex.org/W3171374485","doi":"https://doi.org/10.1145/3447548.3467370","title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","display_name":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3171374485","doi":"https://doi.org/10.1145/3447548.3467370","mag":"3171374485"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.12024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jackson A. Killian","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jackson A. Killian","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arpita Biswas","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arpita Biswas","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sanket Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanket Shah","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":null,"display_name":"Milind Tambe","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Tambe","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":1.4321,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82219792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"871","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9909999966621399,"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/T13553","display_name":"Age of Information Optimization","score":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7069000005722046},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.5350000262260437},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5102999806404114},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.459199994802475},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.44530001282691956},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3725999891757965},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7069000005722046},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6366000175476074},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5037000179290771},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41350001096725464},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C64208722","wikidata":"https://www.wikidata.org/wiki/Q861606","display_name":"Lagrange polynomial","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.12024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.12024","pdf_url":"https://arxiv.org/pdf/2106.12024","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.12024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.12024","pdf_url":"https://arxiv.org/pdf/2106.12024","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981704813","https://openalex.org/W2003798390","https://openalex.org/W2013702609","https://openalex.org/W2044069028","https://openalex.org/W2044502527","https://openalex.org/W2049216612","https://openalex.org/W2056921512","https://openalex.org/W2076556053","https://openalex.org/W2115138651","https://openalex.org/W2141515329","https://openalex.org/W2154204727","https://openalex.org/W2184204218","https://openalex.org/W2809112007","https://openalex.org/W2809254427","https://openalex.org/W2883807213","https://openalex.org/W2913477758","https://openalex.org/W3008966844","https://openalex.org/W3011214669","https://openalex.org/W3189801773"],"related_works":[],"abstract_inverted_index":{"Multi-action":[0,47],"restless":[1],"multi-armed":[2],"bandits":[3],"(RMABs)":[4],"are":[5,18,31],"a":[6,62,78,130,154,171,176],"powerful":[7],"framework":[8],"for":[9,42,46,64,143],"constrained":[10],"resource":[11],"allocation":[12],"in":[13,69],"which":[14,115,134],"N":[15],"independent":[16],"processes":[17],"managed.":[19],"However,":[20,104],"previous":[21],"work":[22],"only":[23],"study":[24],"the":[25,39,66,73,94,136,150,179],"offline":[26],"setting":[27],"where":[28],"problem":[29,122],"dynamics":[30],"known.":[32],"We":[33,76],"address":[34],"this":[35],"restrictive":[36],"assumption,":[37],"designing":[38],"first":[40,58],"algorithms":[41],"learning":[43,108,147,169],"good":[44],"policies":[45],"RMABs":[48,71,145],"online":[49],"using":[50],"combinations":[51],"of":[52,156,186],"Lagrangian":[53],"relaxation":[54],"and":[55,82,85,110,120,138],"Q-learning.":[56,157],"Our":[57],"approach,":[59],"MAIQL,":[60],"extends":[61],"method":[63],"Q-learning":[65],"Whittle":[67],"index":[68],"binary-action":[70],"to":[72,93,117,124,148,182],"multi-action":[74,97,144],"setting.":[75],"derive":[77],"generalized":[79],"update":[80],"rule":[81],"convergence":[83,119],"proof":[84],"establish":[86],"that,":[87],"under":[88],"standard":[89],"assumptions,":[90],"MAIQL":[91,105],"converges":[92],"asymptotically":[95],"optimal":[96],"RMAB":[98],"policy":[99,142],"as":[100,189],"t":[101,190],"\u2192":[102,191],"\u221e.":[103,192],"relies":[106],"on":[107,112,170],"Q-functions":[109],"indexes":[111],"two":[113],"timescales":[114],"leads":[116],"slow":[118],"requires":[121],"structure":[123],"perform":[125],"well.":[126],"Thus,":[127],"we":[128,162,194],"design":[129],"second":[131],"algorithm,":[132],"LPQL,":[133],"learns":[135],"well-performing":[137],"more":[139],"general":[140],"Lagrange":[141,151],"by":[146],"minimize":[149],"bound":[152,185],"through":[153],"variant":[155],"To":[158],"ensure":[159],"fast":[160],"convergence,":[161],"take":[163],"an":[164,183],"approximation":[165],"strategy":[166],"that":[167,196],"enables":[168],"single":[172],"timescale,":[173],"then":[174],"give":[175],"guarantee":[177],"relating":[178],"approximation's":[180],"precision":[181],"upper":[184],"LPQL's":[187],"return":[188],"Finally,":[193],"show":[195],"our":[197],"approaches":[198],"always":[199],"outperform":[200],"baselines":[201],"across":[202],"multiple":[203],"settings,":[204],"including":[205],"one":[206],"derived":[207],"from":[208],"real-world":[209],"medication":[210],"adherence":[211],"data.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-06-22T00:00:00"}