{"id":"https://openalex.org/W7152659297","doi":"https://doi.org/10.48550/arxiv.2604.06738","title":"Beyond Pessimism: Offline Learning in KL-regularized Games","display_name":"Beyond Pessimism: Offline Learning in KL-regularized Games","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152659297","doi":"https://doi.org/10.48550/arxiv.2604.06738"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133313949","display_name":"Yuheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Yuheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133255125","display_name":"Claire Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Claire","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133298876","display_name":"Nan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Nan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133313949"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.6229000091552734,"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":0.6229000091552734,"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":0.2062000036239624,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.05649999901652336,"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/skew","display_name":"Skew","score":0.6499999761581421},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.6186000108718872},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.605400025844574},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5950000286102295},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5419999957084656},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.4390000104904175},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4260999858379364}],"concepts":[{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702999830245972},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4390000104904175},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.36959999799728394},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35120001435279846},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,39,90],"study":[1],"offline":[2,80],"learning":[3,81],"in":[4,82,108],"KL-regularized":[5,49,56,83],"two-player":[6],"zero-sum":[7,84],"games,":[8,50,85],"where":[9],"policies":[10],"are":[11],"optimized":[12],"under":[13],"a":[14,18,41,60,103],"KL":[15],"constraint":[16],"to":[17,29],"fixed":[19],"reference":[20],"policy.":[21],"Prior":[22],"work":[23],"relies":[24],"on":[25,52],"pessimistic":[26],"value":[27],"estimation":[28],"handle":[30],"distribution":[31],"shift,":[32],"yielding":[33],"only":[34],"$\\widetilde{\\mathcal{O}}(1/\\sqrt":[35],"n)$":[36],"statistical":[37,118],"rates.":[38],"develop":[40],"new":[42],"pessimism-free":[43],"algorithm":[44,98],"and":[45,59,99],"analytical":[46],"framework":[47],"for":[48,79],"built":[51],"the":[53,64,73,109,114,121],"smoothness":[54],"of":[55,63,105],"best":[57],"responses":[58],"stability":[61],"property":[62],"Nash":[65],"equilibrium":[66],"induced":[67],"by":[68],"skew":[69],"symmetry.":[70],"This":[71],"yields":[72],"first":[74],"$\\widetilde{\\mathcal{O}}(1/n)$":[75,117],"sample":[76,110],"complexity":[77],"bound":[78],"achieved":[86],"entirely":[87],"without":[88],"pessimism.":[89],"further":[91],"propose":[92],"an":[93],"efficient":[94],"self-play":[95],"policy":[96],"optimization":[97],"prove":[100],"that,":[101],"with":[102],"number":[104],"iterations":[106],"linear":[107],"size,":[111],"it":[112],"achieves":[113],"same":[115],"fast":[116],"rate":[119],"as":[120],"minimax":[122],"estimator.":[123]},"counts_by_year":[],"updated_date":"2026-04-10T06:07:51.998497","created_date":"2026-04-10T00:00:00"}