{"id":"https://openalex.org/W2331759129","doi":"https://doi.org/10.1109/cdc.2016.7799381","title":"Optimal recommendation to users that react: Online learning for a class of POMDPs","display_name":"Optimal recommendation to users that react: Online learning for a class of POMDPs","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2331759129","doi":"https://doi.org/10.1109/cdc.2016.7799381","mag":"2331759129"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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/A5052401633","display_name":"Rahul Meshram","orcid":"https://orcid.org/0000-0003-3966-3269"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rahul Meshram","raw_affiliation_strings":["Electrical Engineering Department, IIT Bombay, Mumbai, INDIA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, IIT Bombay, Mumbai, INDIA","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030430086","display_name":"Aditya Gopalan","orcid":"https://orcid.org/0000-0002-7323-2975"},"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":"Aditya Gopalan","raw_affiliation_strings":["Electrical Communication Engineering Department, Indian Institute of Science, Bangalore, INDIA"],"affiliations":[{"raw_affiliation_string":"Electrical Communication Engineering Department, Indian Institute of Science, Bangalore, INDIA","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017359920","display_name":"D. Manjunath","orcid":"https://orcid.org/0000-0001-7302-284X"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"D. Manjunath","raw_affiliation_strings":["Electrical Engineering Department, IIT Bombay, Mumbai, INDIA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, IIT Bombay, Mumbai, INDIA","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052401633"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":3.7277,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93206728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7210","last_page":"7215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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":0.9972000122070312,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.8706997036933899},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8345730304718018},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.830845296382904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804084300994873},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7506345510482788},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.7429901361465454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6232577562332153},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5987088680267334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5628094673156738},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5353639125823975},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5108377933502197},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5099302530288696},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.47859451174736023},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4413588345050812},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4215041697025299},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.27326634526252747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07965651154518127}],"concepts":[{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.8706997036933899},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8345730304718018},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.830845296382904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804084300994873},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7506345510482788},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.7429901361465454},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6232577562332153},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5987088680267334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5628094673156738},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5353639125823975},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5108377933502197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5099302530288696},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.47859451174736023},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4413588345050812},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4215041697025299},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.27326634526252747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07965651154518127},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/cdc.2016.7799381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:57205","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 Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W148122774","https://openalex.org/W1570963478","https://openalex.org/W1850488217","https://openalex.org/W1901083042","https://openalex.org/W1911551976","https://openalex.org/W1978609982","https://openalex.org/W1991513691","https://openalex.org/W2039522160","https://openalex.org/W2092357578","https://openalex.org/W2103708221","https://openalex.org/W2112420033","https://openalex.org/W2141515329","https://openalex.org/W2153441348","https://openalex.org/W2168405694","https://openalex.org/W2288243449","https://openalex.org/W2298667432","https://openalex.org/W2331759129","https://openalex.org/W2519411794","https://openalex.org/W2536694554","https://openalex.org/W2595897327","https://openalex.org/W2949186496","https://openalex.org/W2963603291","https://openalex.org/W2963713569","https://openalex.org/W2963755386","https://openalex.org/W3020125231","https://openalex.org/W4299366509","https://openalex.org/W6606032028","https://openalex.org/W6639039794","https://openalex.org/W6639904974","https://openalex.org/W6640015871","https://openalex.org/W6645033135","https://openalex.org/W6675595744","https://openalex.org/W6698017823","https://openalex.org/W6726651112"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1850488217","https://openalex.org/W1515117609","https://openalex.org/W3108185025","https://openalex.org/W2964125852","https://openalex.org/W1850547517"],"abstract_inverted_index":{"We":[0,108,125,155],"describe":[1,116],"and":[2,21,31,66,120,142,164,171],"study":[3],"a":[4,15,91,113,128],"model":[5,39,141],"for":[6,49,70,90,103,112,173],"an":[7,85,95],"Automated":[8],"Online":[9],"Recommendation":[10],"System":[11],"(AORS)":[12],"in":[13],"which":[14],"user's":[16],"preferences":[17],"can":[18,22,62],"be":[19],"time-dependent":[20],"also":[23,184],"depend":[24],"on":[25],"the":[26,38,71,110,137,140,146,150,158,161,166,176],"history":[27],"of":[28,37,73,106,139,149,160],"past":[29],"recommendations":[30,61],"play-outs.":[32],"The":[33,80],"three":[34],"key":[35],"features":[36],"that":[40],"makes":[41],"it":[42,68],"more":[43],"realistic":[44],"compared":[45],"to":[46,135,152,175],"existing":[47],"models":[48],"recommendation":[50],"systems":[51],"are":[52,183],"(1)":[53],"user":[54],"preference":[55],"is":[56,82],"inherently":[57],"latent,":[58],"(2)":[59],"current":[60],"affect":[63],"future":[64],"preferences,":[65],"(3)":[67],"allows":[69],"development":[72],"learning":[74,133,162],"algorithms":[75],"with":[76,94],"provable":[77],"performance":[78,159],"guarantees.":[79],"problem":[81,182],"cast":[83],"as":[84],"average-cost":[86],"restless":[87,177],"multi-armed":[88,180],"bandit":[89,181],"given":[92],"user,":[93],"independent":[96],"partially":[97],"observable":[98],"Markov":[99,179],"decision":[100],"process":[101],"(POMDP)":[102],"each":[104],"item":[105],"content.":[107],"analyze":[109,157],"POMDP":[111],"single":[114],"arm,":[115],"its":[117,122],"structural":[118],"properties,":[119],"characterize":[121,165],"optimal":[123],"policy.":[124],"then":[126,156],"develop":[127],"Thompson":[129],"sampling-based":[130],"online":[131],"reinforcement":[132],"algorithm":[134,163],"learn":[136],"parameters":[138],"optimize":[143],"utility":[144],"from":[145],"binary":[147],"responses":[148],"users":[151],"continuous":[153],"recommendations.":[154],"regret.":[167],"Illustrative":[168],"numerical":[169],"results":[170],"directions":[172],"extension":[174],"hidden":[178],"presented.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}