{"id":"https://openalex.org/W4415949755","doi":"https://doi.org/10.1145/3801489.3806884","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","display_name":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W4415949755","doi":"https://doi.org/10.1145/3801489.3806884"},"language":"en","primary_location":{"id":"doi:10.1145/3801489.3806884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801489.3806884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Phalguni Nanda","orcid":"https://orcid.org/0000-0002-1972-8582"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phalguni Nanda","raw_affiliation_strings":["Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0002-1972-8582","affiliations":[{"raw_affiliation_string":"Industrial Engineering, Purdue University, West Lafayette, Indiana, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058269077","display_name":"Zaiwei Chen","orcid":"https://orcid.org/0000-0001-9915-5595"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaiwei Chen","raw_affiliation_strings":["Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0001-9915-5595","affiliations":[{"raw_affiliation_string":"Industrial Engineering, Purdue University, West Lafayette, Indiana, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01322561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8938000202178955,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8938000202178955,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.07129999995231628,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.010200000368058681,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7281000018119812},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5892999768257141},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5382999777793884},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/stochastic-matrix","display_name":"Stochastic matrix","score":0.4903999865055084},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4855000078678131},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4618000090122223},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4575999975204468}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7281000018119812},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.4903999865055084},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48190000653266907},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.46880000829696655},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4618000090122223},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4575999975204468},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4512999951839447},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41370001435279846},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C10431821","wikidata":"https://www.wikidata.org/wiki/Q6510174","display_name":"Learning effect","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3801489.3806884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},{"id":"doi:10.1145/3805624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805624","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.16132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.16132","pdf_url":"https://arxiv.org/pdf/2510.16132","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.16132","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.16132","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3801489.3806884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-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":{"In":[0],"this":[1],"work,":[2],"we":[3,164],"present":[4],"the":[5,28,40,96,106,127,140,170,191,199,207,211,218],"first":[6],"finite-time":[7,87],"analysis":[8,197,219],"of":[9,30,58,71,142,169,198,220],"Q-learning":[10],"with":[11,75,174,203,225],"time-varying":[12,144,227],"learning":[13,97,121,128,145,212,223,228],"policies":[14],"(i.e.,":[15],"on-policy":[16,110,120],"sampling)":[17],"for":[18,49,61,89],"discounted":[19],"Markov":[20,37],"decision":[21],"processes":[22],"under":[23],"minimal":[24,153],"assumptions,":[25],"requiring":[26],"only":[27],"existence":[29],"a":[31,45,55,76,137,166,175,182,195],"policy":[32,98,129],"that":[33,70],"induces":[34],"an":[35,85,123,133],"irreducible":[36],"chain":[38],"over":[39],"state":[41],"space.":[42],"We":[43,82,188],"establish":[44],"last-iterate":[46],"convergence":[47],"rate":[48,68,88],"E[||Qk":[50,63],"-":[51,64,91],"Q*||\u221e2],":[52,92],"which":[53,147],"implies":[54],"sample":[56],"complexity":[57],"order":[59],"O(1/\u03be2)":[60],"achieving":[62],"Q*||\u221e]\u2264":[65],"\u03be.":[66],"This":[67],"matches":[69],"off-policy":[72,118],"Q-learning,":[73],"but":[74],"worse":[77],"dependence":[78],"on":[79],"exploration-related":[80],"parameters.":[81],"also":[83],"derive":[84],"explicit":[86],"E[||Q\u03c0k":[90],"where":[93],"\u03c0k":[94],"denotes":[95],"at":[99],"iteration":[100],"k.":[101],"Together,":[102],"these":[103,162],"results":[104],"highlight":[105],"exploration--exploitation":[107],"trade-off":[108],"in":[109,117],"Q-learning.":[111],"While":[112],"exploration":[113,154],"is":[114],"weaker":[115],"than":[116],"methods,":[119],"enjoys":[122],"exploitation":[124],"advantage":[125],"since":[126],"itself":[130],"converges":[131],"to":[132,205],"optimal":[134],"one.":[135],"From":[136],"technical":[138],"perspective,":[139],"combination":[141],"rapidly":[143,226],"policies,":[146,229],"induce":[148],"time-inhomogeneous":[149],"Markovian":[150,171],"noise,":[151],"and":[152,185,210,235],"assumptions":[155],"presents":[156],"significant":[157],"analytical":[158],"challenges.":[159],"To":[160],"address":[161],"challenges,":[163],"develop":[165],"Poisson-equation-based":[167],"decomposition":[168],"noise":[172],"associated":[173],"lazy":[176],"transition":[177],"matrix,":[178],"separating":[179],"it":[180],"into":[181],"martingale-difference":[183],"term":[184],"residual":[186,192],"terms.":[187],"then":[189],"control":[190],"terms":[193],"through":[194],"sensitivity":[196],"Poisson":[200],"equation":[201],"solution":[202],"respect":[204],"both":[206],"Q-function":[208],"estimate":[209],"policy.":[213],"These":[214],"techniques":[215],"may":[216],"facilitate":[217],"other":[221],"reinforcement":[222],"algorithms":[224],"such":[230],"as":[231],"single-timescale":[232],"actor--critic":[233],"methods":[234],"learning-in-games":[236],"algorithms.":[237]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-22T00:00:00"}