{"id":"https://openalex.org/W2798518493","doi":"https://doi.org/10.1145/3184558.3191630","title":"Stochastic Multi-path Routing Problem with Non-stationary Rewards","display_name":"Stochastic Multi-path Routing Problem with Non-stationary Rewards","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798518493","doi":"https://doi.org/10.1145/3184558.3191630","mag":"2798518493"},"language":"en","primary_location":{"id":"doi:10.1145/3184558.3191630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191630","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191630&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3191630&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008979402","display_name":"Pankaj Trivedi","orcid":"https://orcid.org/0000-0003-0173-2804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pankaj Trivedi","raw_affiliation_strings":["PayU Payments Pvt Ltd, Gurgaon, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PayU Payments Pvt Ltd, Gurgaon, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061034676","display_name":"Arvind Kumar Singh","orcid":"https://orcid.org/0000-0002-5543-1081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arvind Singh","raw_affiliation_strings":["PayU Payments Pvt Ltd, Gurgaon, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PayU Payments Pvt Ltd, Gurgaon, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1707","last_page":"1712"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9993000030517578,"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/T11182","display_name":"Auction Theory and Applications","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7216939330101013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7008346319198608},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.6024700403213501},{"id":"https://openalex.org/keywords/payment","display_name":"Payment","score":0.5952650904655457},{"id":"https://openalex.org/keywords/gateway","display_name":"Gateway (web page)","score":0.5470158457756042},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5340605974197388},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5173389315605164},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.46720048785209656},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4390287399291992},{"id":"https://openalex.org/keywords/interior-gateway-protocol","display_name":"Interior gateway protocol","score":0.4383723735809326},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.42347198724746704},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3560827374458313},{"id":"https://openalex.org/keywords/static-routing","display_name":"Static routing","score":0.30806398391723633},{"id":"https://openalex.org/keywords/routing-protocol","display_name":"Routing protocol","score":0.2497539520263672},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14560869336128235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10961577296257019},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10956481099128723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08530929684638977}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7216939330101013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008346319198608},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.6024700403213501},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.5952650904655457},{"id":"https://openalex.org/C2777710495","wikidata":"https://www.wikidata.org/wiki/Q5527195","display_name":"Gateway (web page)","level":2,"score":0.5470158457756042},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5340605974197388},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5173389315605164},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.46720048785209656},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4390287399291992},{"id":"https://openalex.org/C52837422","wikidata":"https://www.wikidata.org/wiki/Q431028","display_name":"Interior gateway protocol","level":5,"score":0.4383723735809326},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.42347198724746704},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3560827374458313},{"id":"https://openalex.org/C204948658","wikidata":"https://www.wikidata.org/wiki/Q1119410","display_name":"Static routing","level":4,"score":0.30806398391723633},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.2497539520263672},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14560869336128235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10961577296257019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10956481099128723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08530929684638977},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3184558.3191630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191630","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191630&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3184558.3191630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191630","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191630&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798518493.pdf","grobid_xml":"https://content.openalex.org/works/W2798518493.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W46877293","https://openalex.org/W1549884163","https://openalex.org/W1552540037","https://openalex.org/W1911551976","https://openalex.org/W2014482607","https://openalex.org/W2030500137","https://openalex.org/W2030501831","https://openalex.org/W2049934117","https://openalex.org/W2058879737","https://openalex.org/W2108738385","https://openalex.org/W2113690490","https://openalex.org/W2115905049","https://openalex.org/W2124832196","https://openalex.org/W2131101582","https://openalex.org/W2131953851","https://openalex.org/W2157723363","https://openalex.org/W2158125716","https://openalex.org/W2168405694","https://openalex.org/W2173246629","https://openalex.org/W2949186496","https://openalex.org/W2950929549","https://openalex.org/W3049584421","https://openalex.org/W3125634603","https://openalex.org/W4246270964"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4292701710","https://openalex.org/W306110616","https://openalex.org/W1585786976"],"abstract_inverted_index":{"Payment":[0],"transaction":[1,17,39,80],"engine":[2,27],"at":[3,136],"PayU":[4],"processes":[5],"multimillion":[6],"trans-":[7],"actions":[8],"every":[9,38],"day":[10],"through":[11,18],"multiple":[12],"payment":[13,21,47],"gateways.":[14],"Routing":[15],"a":[16,60,63,74,172,187,203],"an":[19,51,196,199,215],"appropriate":[20],"gateway":[22,61,75,85,135,173],"is":[23,36,62,76,81,97,148,157,169,186],"crucial":[24],"to":[25,41,98,119,144,150,158,170,175,233,236],"the":[26,30,84,100,114,133,137,140,152,160,164,180,211],"for":[28,59,73],"optimizing":[29,128],"availability":[31],"and":[32,68,162,206],"cost.":[33],"The":[34,57,71,92,154,166,183],"problem":[35,185],"that":[37,220],"needs":[40,118],"choose":[42,171],"one":[43],"of":[44,65,94,108,178,190,213],"K":[45],"available":[46],"gateways":[48,124],"characterized":[49],"by":[50,83,87,131],"unknown":[52],"probability":[53,177],"reward":[54,58,72],"distri-":[55],"bution.":[56],"combination":[64],"its":[66,88,176],"health":[67],"cost":[69],"factors.":[70],"only":[77],"realized":[78],"when":[79],"processed":[82],"i.e.":[86],"success":[89],"or":[90,218],"failure.":[91],"objective":[93,156],"dynamic":[95,115],"routing":[96,184],"maximize":[99,163],"cumulative":[101],"expected":[102],"rewards":[103,130],"over":[104],"some":[105,222],"given":[106],"horizon":[107],"transactions'":[109],"life.":[110],"To":[111],"do":[112],"this,":[113],"switching":[116],"system":[117],"acquire":[120],"informa-":[121],"tion":[122],"about":[123],"(exploration)":[125],"while":[126],"simultaneously":[127],"immediate":[129],"selecting":[132],"best":[134,181],"moment":[138],"(exploitation);":[139],"price":[141],"paid":[142],"due":[143],"this":[145],"trade":[146],"o":[147],"referred":[149],"as":[151],"regret.":[153],"main":[155],"minimize":[159],"regret":[161],"rewards.":[165],"basic":[167],"idea":[168],"according":[174],"being":[179],"gateway.":[182],"direct":[188],"formulation":[189],"reinforcement":[191],"learning":[192],"(RL)":[193],"problem.":[194],"In":[195],"RL":[197],"problem,":[198],"agent":[200],"interacts":[201],"with":[202,210],"dynamic,":[204],"stochastic,":[205],"incompletely":[207],"known":[208],"environment,":[209],"goal":[212],"finding":[214],"action-selection":[216],"strategy,":[217],"policy,":[219],"optimizes":[221],"long-term":[223],"performance":[224],"measure.":[225],"Thompson":[226],"Sampling":[227],"algorithm":[228],"has":[229],"experimentally":[230],"been":[231],"shown":[232],"be":[234],"close":[235],"optimal.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
