{"id":"https://openalex.org/W7220672912","doi":"https://doi.org/10.48550/arxiv.2610.05428","title":"Learning in Continuous Games from Pairwise Preference Feedback","display_name":"Learning in Continuous Games from Pairwise Preference Feedback","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220672912","doi":"https://doi.org/10.48550/arxiv.2610.05428"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05428","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05428","pdf_url":"https://arxiv.org/pdf/2610.05428","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.05428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065250840","display_name":"Anas Barakat","orcid":"https://orcid.org/0000-0002-2527-3748","observed_orcids":["https://orcid.org/0000-0002-2527-3748"]},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Barakat, Anas","raw_affiliation_strings":["Singapore University of Technology and Design "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design ","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065250840"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9731000065803528,"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/T11031","display_name":"Game Theory and Applications","score":0.9731000065803528,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.01979999989271164,"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":0.0007999999797903001,"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/continuous-games","display_name":"continuous games","score":0.8220000267028809},{"id":"https://openalex.org/keywords/ordinal-preferences","display_name":"ordinal preferences","score":0.46399998664855957},{"id":"https://openalex.org/keywords/coarse-correlated-equilibrium","display_name":"coarse correlated equilibrium","score":0.9290000200271606},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6290000081062317},{"id":"https://openalex.org/keywords/ordinal-potential-games","display_name":"ordinal potential games","score":0.8149999976158142},{"id":"https://openalex.org/keywords/last-iterate-convergence","display_name":"last-iterate convergence","score":0.8690000176429749}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.84579998254776},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8076000213623047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6789000034332275},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.660099983215332},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6384000182151794},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.5063999891281128},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.4564000070095062},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2781043087","wikidata":"https://www.wikidata.org/wiki/Q939761","display_name":"Preference theory","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C110313322","wikidata":"https://www.wikidata.org/wiki/Q7100793","display_name":"Ordinal regression","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05428","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05428","pdf_url":"https://arxiv.org/pdf/2610.05428","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.05428","doi":"https://doi.org/10.48550/arxiv.2610.05428","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05428","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.05428","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05428","pdf_url":"https://arxiv.org/pdf/2610.05428","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220672912.pdf","grobid_xml":"https://content.openalex.org/works/W7220672912.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2800922801","https://openalex.org/W4417529801","https://openalex.org/W7128472215","https://openalex.org/W7158749655","https://openalex.org/W7160845428","https://openalex.org/W7203684841"],"related_works":["https://openalex.org/W3000234344","https://openalex.org/W2809791077","https://openalex.org/W7203621232","https://openalex.org/W2949909914","https://openalex.org/W7139961856","https://openalex.org/W2150170179","https://openalex.org/W7096871840","https://openalex.org/W3124454824","https://openalex.org/W7099859565","https://openalex.org/W7096000320"],"abstract_inverted_index":{"We":[0,27,111,127],"study":[1],"learning":[2],"in":[3,57,161],"continuous":[4],"games":[5],"when":[6],"players":[7],"receive":[8],"only":[9],"pairwise":[10,139],"preference":[11,25,99,182],"feedback,":[12],"revealing":[13],"which":[14],"of":[15,49],"two":[16,58],"actions":[17],"is":[18],"preferred":[19],"but":[20],"neither":[21],"payoff":[22],"values":[23],"nor":[24],"magnitudes.":[26],"first":[28],"show":[29,112],"that":[30,65,113],"standard":[31],"external":[32],"regret":[33,56,105,120,155],"and":[34,54,107,146,177],"coarse":[35],"correlated":[36],"equilibria":[37],"(CCE)":[38],"are":[39,77],"not":[40],"identifiable":[41],"from":[42,137,181],"this":[43,87],"ordinal":[44,93,103,119,154,162],"information:":[45],"the":[46,63,74,148,169],"same":[47,75],"sequence":[48],"play":[50],"can":[51],"incur":[52],"zero":[53],"linear":[55],"ordinally":[59],"equivalent":[60],"games,":[61,164],"while":[62],"distributions":[64],"remain":[66],"CCE":[67],"across":[68],"all":[69],"cardinal":[70,186],"representations":[71],"consistent":[72],"with":[73],"preferences":[76],"exactly":[78],"those":[79],"supported":[80],"on":[81,96],"pure":[82],"Nash":[83,170],"equilibria.":[84],"Motivated":[85],"by":[86],"gap,":[88],"we":[89],"develop":[90],"a":[91,130],"first-order":[92],"theory":[94],"based":[95],"normalized":[97],"unilateral":[98],"directions,":[100],"introducing":[101],"an":[102],"directional":[104],"benchmark":[106],"corresponding":[108],"equilibrium":[109,178],"notions.":[110],"block-normalized":[114],"pseudogradient":[115],"dynamics":[116,136],"achieve":[117],"sublinear":[118,152],"and,":[121,160],"under":[122],"additional":[123],"structure,":[124],"Nash-convergence":[125],"guarantees.":[126],"then":[128],"use":[129],"single-comparison":[131],"estimator":[132],"to":[133,168],"implement":[134],"these":[135],"finite":[138],"comparisons.":[140],"With":[141],"one":[142],"comparison":[143],"per":[144],"player":[145],"round,":[147],"resulting":[149],"algorithm":[150],"achieves":[151],"finite-resolution":[153],"against":[156],"arbitrary":[157],"opponent":[158],"behavior":[159],"potential":[163],"almost-sure":[165],"last-iterate":[166],"convergence":[167],"set.":[171],"Our":[172],"results":[173],"provide":[174],"regret,":[175],"dynamics,":[176],"guarantees":[179],"directly":[180],"feedback":[183],"without":[184],"reconstructing":[185],"utilities.":[187]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}