{"id":"https://openalex.org/W3167401935","doi":"https://doi.org/10.1109/tnnls.2021.3085088","title":"A Reinforcement Learning Approach to Price Cloud Resources With Provable Convergence Guarantees","display_name":"A Reinforcement Learning Approach to Price Cloud Resources With Provable Convergence Guarantees","publication_year":2021,"publication_date":"2021-06-10","ids":{"openalex":"https://openalex.org/W3167401935","doi":"https://doi.org/10.1109/tnnls.2021.3085088","mag":"3167401935","pmid":"https://pubmed.ncbi.nlm.nih.gov/34111014"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3085088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3085088","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5064190343","display_name":"Hong Xie","orcid":"https://orcid.org/0000-0001-7935-7210"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Xie","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-7935-7210","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068489266","display_name":"John C. S. Lui","orcid":"https://orcid.org/0000-0001-7466-0384"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"John C. S. Lui","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7466-0384","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78122094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":"12","first_page":"7448","last_page":"7460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9868000149726868,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/dynamic-pricing","display_name":"Dynamic pricing","score":0.7793103456497192},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7044206857681274},{"id":"https://openalex.org/keywords/revenue-management","display_name":"Revenue management","score":0.6954368352890015},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6760290861129761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6689108610153198},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5932406783103943},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5701438784599304},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.48364365100860596},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.47437769174575806},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46732014417648315},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4332050681114197},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2570122480392456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23157960176467896},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.19912344217300415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1662745475769043},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.16513532400131226},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1574627161026001},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.09616315364837646}],"concepts":[{"id":"https://openalex.org/C2779391423","wikidata":"https://www.wikidata.org/wiki/Q17009728","display_name":"Dynamic pricing","level":2,"score":0.7793103456497192},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7044206857681274},{"id":"https://openalex.org/C2781386248","wikidata":"https://www.wikidata.org/wiki/Q11898700","display_name":"Revenue management","level":3,"score":0.6954368352890015},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6760290861129761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689108610153198},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5932406783103943},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5701438784599304},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.48364365100860596},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.47437769174575806},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46732014417648315},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4332050681114197},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2570122480392456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23157960176467896},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.19912344217300415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1662745475769043},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.16513532400131226},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1574627161026001},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.09616315364837646},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3085088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3085088","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34111014","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34111014","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5805885788","display_name":"Reinforcement Learning Approach to Community Exploration in Network Science Problems: Theory and applications","funder_award_id":"14200420","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2009533501","https://openalex.org/W2013275264","https://openalex.org/W2025616337","https://openalex.org/W2046660101","https://openalex.org/W2102558581","https://openalex.org/W2106121006","https://openalex.org/W2125053293","https://openalex.org/W2132727135","https://openalex.org/W2136041258","https://openalex.org/W2138583691","https://openalex.org/W2149274247","https://openalex.org/W2153998850","https://openalex.org/W2275918351","https://openalex.org/W2334782222","https://openalex.org/W2505919521","https://openalex.org/W2514619461","https://openalex.org/W2527855297","https://openalex.org/W2595166142","https://openalex.org/W2607684270","https://openalex.org/W2620387295","https://openalex.org/W2810926567","https://openalex.org/W2905057216","https://openalex.org/W2922729526","https://openalex.org/W2996741051","https://openalex.org/W3011120880","https://openalex.org/W3122917641","https://openalex.org/W3125082764","https://openalex.org/W3125785906","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4250589301","https://openalex.org/W6694662636","https://openalex.org/W6734681594","https://openalex.org/W6743500281","https://openalex.org/W6752610953","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2420409956","https://openalex.org/W4388340416","https://openalex.org/W2029598999","https://openalex.org/W2895891960","https://openalex.org/W2740158290","https://openalex.org/W1997881597","https://openalex.org/W4389475841","https://openalex.org/W4213334555","https://openalex.org/W2950385751","https://openalex.org/W1574958246"],"abstract_inverted_index":{"How":[0,30,41],"to":[1,7,31,38,42,49,69,84,106,122,126,152,172],"generate":[2],"more":[3,22],"revenues":[4],"is":[5],"crucial":[6],"cloud":[8,14],"providers.":[9],"Evidences":[10],"from":[11,111],"the":[12,33,44,51,71,75,86,92,95,103,108,120,127,137,141,144,153,168,173,183,193,201,220],"Amazon":[13],"system":[15],"indicate":[16],"that":[17,147,182],"\"dynamic":[18],"pricing\"":[19],"would":[20],"be":[21],"profitable":[23],"than":[24],"\"static":[25],"pricing.\"":[26],"The":[27],"challenges":[28],"are:":[29],"set":[32],"price":[34,45,88,110],"in":[35],"real-time":[36,209],"so":[37,48],"maximize":[39],"revenues?":[40],"estimate":[43],"dependent":[46],"demand":[47],"optimize":[50],"pricing":[52,61,222],"decision?":[53],"We":[54,78,101,162],"first":[55],"design":[56],"a":[57,65,80,178,187],"discrete-time":[58],"based":[59],"dynamic":[60,210],"scheme":[62],"and":[63,89,98,115,207,213],"formulate":[64,79],"Markov":[66],"decision":[67],"process":[68],"characterize":[70,91],"evolving":[72],"dynamics":[73],"of":[74,94,143,189],"price-dependent":[76],"demand.":[77],"revenue":[81,97,146,194],"maximization":[82],"framework":[83],"determine":[85],"optimal":[87,96,99,109,128,145,174],"theoretically":[90],"\"structure\"":[93],"price.":[100],"apply":[102],"Q":[104,156,202,205],"-learning":[105,157],"infer":[107],"historical":[112],"transaction":[113],"data":[114],"derive":[116,163],"sufficient":[117,164],"conditions":[118],"on":[119,177],"model":[121],"guarantee":[123],"its":[124],"convergence":[125],"price,":[129],"but":[130],"it":[131],"converges":[132,171],"slowly.":[133],"To":[134],"speed":[135],"up":[136],"convergence,":[138],"we":[139,148],"incorporate":[140],"structure":[142],"obtained":[149],"earlier,":[150],"leading":[151],"VpQ-learning":[154,169,184],"(":[155],"with":[158],"value":[159],"projection)":[160],"algorithm.":[161],"conditions,":[165],"under":[166],"which":[167],"algorithm":[170,185],"policy.":[175],"Experiments":[176],"real-world":[179],"dataset":[180],"show":[181],"outperforms":[186],"variety":[188],"baselines,":[190],"i.e.,":[191],"improves":[192],"by":[195,214],"as":[196,198,215,217],"high":[197,216],"50%":[199],"over":[200,219],"-learning,":[203,206],"speedy":[204],"adaptive":[208],"programming":[211],"(ARTDP),":[212],"20%":[218],"fixed":[221],"scheme.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}