{"id":"https://openalex.org/W4363620180","doi":"https://doi.org/10.1109/ciss56502.2023.10089744","title":"Multi-armed Bandit Learning on a Graph","display_name":"Multi-armed Bandit Learning on a Graph","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4363620180","doi":"https://doi.org/10.1109/ciss56502.2023.10089744"},"language":"en","primary_location":{"id":"doi:10.1109/ciss56502.2023.10089744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss56502.2023.10089744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","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/A5103163516","display_name":"Tianpeng Zhang","orcid":"https://orcid.org/0000-0001-8700-8715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianpeng Zhang","raw_affiliation_strings":["Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA","Harvard School of Engineering and Applied Sciences, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA","institution_ids":[]},{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070727806","display_name":"Kasper Johansson","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kasper Johansson","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,Stanford,CA,USA","Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA","Harvard School of Engineering and Applied Sciences, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA","institution_ids":[]},{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3332,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81334693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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/T12288","display_name":"Optimization and Search Problems","score":0.996999979019165,"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/graph","display_name":"Graph","score":0.5751665234565735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5643841028213501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.478250652551651},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.47807741165161133},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3828316032886505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3805745840072632},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.35432201623916626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3412398397922516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2932232618331909}],"concepts":[{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5751665234565735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5643841028213501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.478250652551651},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.47807741165161133},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3828316032886505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3805745840072632},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.35432201623916626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3412398397922516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2932232618331909}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss56502.2023.10089744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss56502.2023.10089744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W100039866","https://openalex.org/W1916369423","https://openalex.org/W2000850397","https://openalex.org/W2016647253","https://openalex.org/W2077902449","https://openalex.org/W2105066050","https://openalex.org/W2108234048","https://openalex.org/W2604272474","https://openalex.org/W2755613412","https://openalex.org/W2769648743","https://openalex.org/W2980781235","https://openalex.org/W2982052355","https://openalex.org/W3020125231","https://openalex.org/W3121632328","https://openalex.org/W3124921858","https://openalex.org/W3135643734","https://openalex.org/W3214337575","https://openalex.org/W4206275166","https://openalex.org/W4206530644","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4225548403","https://openalex.org/W4255405898","https://openalex.org/W4287203049","https://openalex.org/W4363620180","https://openalex.org/W6604079820","https://openalex.org/W6639039794","https://openalex.org/W6675713325","https://openalex.org/W6676301642","https://openalex.org/W6681980492","https://openalex.org/W6736209634","https://openalex.org/W6752725515","https://openalex.org/W6769707886","https://openalex.org/W6779124110","https://openalex.org/W6791654189","https://openalex.org/W6794474540"],"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/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247"],"abstract_inverted_index":{"The":[0,76],"multi-armed":[1],"bandit(MAB)":[2],"problem":[3],"is":[4,96,154,163,189],"a":[5,35,66,119],"simple":[6],"yet":[7],"powerful":[8],"framework":[9],"that":[10,38,123,134,208],"has":[11],"been":[12],"extensively":[13],"studied":[14],"in":[15,82,196],"the":[16,40,43,58,70,79,84,93,100,113,128,155,164,167,171,191],"context":[17],"of":[18,42,55,115,130,157,166],"decision-making":[19],"under":[20],"uncertainty.":[21],"In":[22],"many":[23],"real-world":[24],"applications,":[25,29],"such":[26],"as":[27],"robotic":[28],"selecting":[30,83],"an":[31,53,62,107],"arm":[32],"corresponds":[33],"to":[34,68,181],"physical":[36],"action":[37],"constrains":[39],"choices":[41],"next":[44,85],"available":[45,86],"arms":[46],"(actions).":[47],"Motivated":[48],"by":[49],"this,":[50],"we":[51,117],"study":[52],"extension":[54],"MAB":[56],"called":[57],"graph":[59,67,77,94],"bandit,":[60],"where":[61,149],"agent":[63],"travels":[64],"over":[65],"maximize":[69],"reward":[71,101],"collected":[72],"from":[73],"different":[74],"nodes.":[75],"defines":[78],"agent's":[80],"freedom":[81],"nodes":[87,158],"at":[88],"each":[89],"step.":[90],"We":[91,132],"assume":[92],"structure":[95],"fully":[97],"available,":[98],"but":[99],"distributions":[102],"are":[103],"unknown.":[104],"Built":[105],"upon":[106],"offline":[108],"graph-based":[109],"planning":[110],"algorithm":[111,137,210],"and":[112,159],"principle":[114,129],"optimism,":[116],"design":[118],"learning":[120,147,199],"algorithm,":[121],"G-UCB,":[122],"balances":[124],"long-term":[125],"exploration-exploitation":[126],"using":[127],"optimism.":[131],"show":[133],"our":[135,185,209],"proposed":[136],"achieves":[138],"<tex":[139,150,160,175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140,151,161,176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">${O}(\\sqrt{\\vert":[141],"S\\vert":[142,144,178],"T\\log(T)}+D\\vert":[143],"\\log":[145],"T)$</tex>":[146],"regret,":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\vert":[152],"S\\vert$</tex>":[153],"number":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$D$</tex>":[162],"diameter":[165],"graph,":[168],"which":[169],"matches":[170],"theoretical":[172],"lower":[173],"bound":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\Omega(\\sqrt{\\vert":[177],"T})$</tex>":[179],"up":[180],"logarithmic":[182],"factors.":[183],"To":[184],"knowledge,":[186],"this":[187],"result":[188],"among":[190],"first":[192],"tight":[193],"regret":[194],"bounds":[195],"non-episodic,":[197],"un-discounted":[198],"problems":[200],"with":[201],"known":[202],"deterministic":[203],"transitions.":[204],"Numerical":[205],"experiments":[206],"confirm":[207],"outperforms":[211],"several":[212],"benchmarks.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}