{"id":"https://openalex.org/W7124313441","doi":"https://doi.org/10.65109/wbsd5535","title":"Equilibrium Bandits: Learning Optimal Equilibria of Unknown Dynamics","display_name":"Equilibrium Bandits: Learning Optimal Equilibria of Unknown Dynamics","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W7124313441","doi":"https://doi.org/10.65109/wbsd5535"},"language":"en","primary_location":{"id":"doi:10.65109/wbsd5535","doi":"https://doi.org/10.65109/wbsd5535","is_oa":false,"landing_page_url":"https://doi.org/10.65109/wbsd5535","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.13653","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057820085","display_name":"Siddharth Chandak","orcid":"https://orcid.org/0000-0003-3237-7729","observed_orcids":["https://orcid.org/0000-0003-3237-7729"]},"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":"Siddharth Chandak","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020882454","display_name":"Ilai Bistritz","orcid":"https://orcid.org/0000-0002-4120-8292","observed_orcids":["https://orcid.org/0000-0002-4120-8292"]},"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":"Ilai Bistritz","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002056995","display_name":"Nicholas Bambos","orcid":"https://orcid.org/0000-0001-9250-4553","observed_orcids":["https://orcid.org/0000-0001-9250-4553"]},"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":"Nicholas Bambos","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.3465,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87371002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1336","last_page":"1344"},"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"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/unknown-dynamics","display_name":"unknown dynamics","score":0.5699999928474426},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.652999997138977},{"id":"https://openalex.org/keywords/convergence-to-equilibrium","display_name":"convergence to equilibrium","score":0.7319999933242798},{"id":"https://openalex.org/keywords/concentration-bounds","display_name":"concentration bounds","score":0.5270000100135803},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.6869999766349792},{"id":"https://openalex.org/keywords/epidemic-control","display_name":"epidemic control","score":0.9470000267028809},{"id":"https://openalex.org/keywords/game-control","display_name":"game control","score":0.9480000138282776}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7287999987602234},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5400999784469604},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4966999888420105},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36239999532699585},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C41949839","wikidata":"https://www.wikidata.org/wiki/Q1756677","display_name":"Stability theory","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C94766913","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium point","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.31859999895095825},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C2993812969","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium solution","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.65109/wbsd5535","doi":"https://doi.org/10.65109/wbsd5535","is_oa":false,"landing_page_url":"https://doi.org/10.65109/wbsd5535","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.13653","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.13653","pdf_url":"https://arxiv.org/pdf/2302.13653","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.13653","doi":"https://doi.org/10.48550/arxiv.2302.13653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.13653","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.13653","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.13653","pdf_url":"https://arxiv.org/pdf/2302.13653","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124313441.pdf","grobid_xml":"https://content.openalex.org/works/W7124313441.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2920567230"],"related_works":["https://openalex.org/W1996232327","https://openalex.org/W7097714502","https://openalex.org/W3084085014","https://openalex.org/W4399117257","https://openalex.org/W2168509539","https://openalex.org/W2947437348","https://openalex.org/W7124131739","https://openalex.org/W7100137794","https://openalex.org/W7221800776","https://openalex.org/W2752505153"],"abstract_inverted_index":{"Consider":[0],"a":[1,38,42,61,119,169],"decision-maker":[2,71],"that":[3,128,166,195],"can":[4,58],"pick":[5],"one":[6],"out":[7],"of":[8,44,49,67,171,205,223],"K":[9],"actions":[10,20],"to":[11,37,54,73,96,98,130,141,155,190],"control":[12,198,201],"an":[13,132],"unknown":[14,53],"system,":[15],"for":[16,93,114,176,221],"T":[17,80],"turns.":[18,81],"The":[19,47,70],"are":[21,52,85,202],"interpreted":[22],"as":[23,41],"different":[24],"configurations":[25],"or":[26,108],"policies.":[27],"Holding":[28],"the":[29,33,50,55,65,79,94,144,159,184,214],"same":[30],"action":[31,133],"fixed,":[32],"system":[34,51,95,160],"asymptotically":[35],"converges":[36],"unique":[39],"equilibrium,":[40],"function":[43],"this":[45,115,177],"action.":[46],"dynamics":[48],"decision-maker,":[56],"which":[57],"only":[59],"observe":[60],"noisy":[62],"reward":[63,77],"at":[64],"end":[66],"every":[68],"turn.":[69],"wants":[72],"maximize":[74],"its":[75],"accumulated":[76],"over":[78],"Learning":[82],"what":[83],"equilibria":[84],"better":[86],"results":[87],"in":[88],"higher":[89],"rewards,":[90],"but":[91],"waiting":[92],"converge":[97],"equilibrium":[99,145,206],"costs":[100],"valuable":[101],"time.":[102],"Existing":[103],"bandit":[104,179],"algorithms,":[105],"either":[106],"stochastic":[107],"adversarial,":[109],"achieve":[110],"linear":[111],"(trivial)":[112],"regret":[113,170],"problem.":[116],"We":[117,164,192,216],"present":[118],"novel":[120],"algorithm,":[121],"termed":[122],"Upper":[123],"Equilibrium":[124],"Concentration":[125],"Bound":[126],"(UECB),":[127],"knows":[129],"switch":[131],"quickly":[134],"if":[135],"it":[136,140],"is":[137,146,149,161,183],"not":[138],"worth":[139],"wait":[142],"until":[143],"reached.":[147],"This":[148],"enabled":[150],"by":[151],"employing":[152],"'convergence":[153],"bounds'":[154],"determine":[156],"how":[157],"far":[158],"from":[162],"equilibrium.":[163,191],"prove":[165],"UECB":[167,219],"achieves":[168],"O(log(T)+\u03c4c":[172],"log(\u03c4c)+\u03c4c":[173],"log":[174,210],"log(T))":[175],"\"equilibrium":[178],"problem\"":[180],"where":[181,208],"\u03c4c":[182,209,211],"worst":[185],"case":[186],"approximate":[187],"convergence":[188],"time":[189],"then":[193,217],"show":[194],"both":[196,222],"epidemic":[197],"and":[199],"game":[200],"special":[203],"cases":[204],"bandits,":[207],"typically":[212],"dominates":[213],"regret.":[215],"test":[218],"numerically":[220],"these":[224],"applications.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-01-16T00:00:00"}