{"id":"https://openalex.org/W4415798366","doi":"https://doi.org/10.52202/079017-0972","title":"Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation","display_name":"Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415798366","doi":"https://doi.org/10.52202/079017-0972"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0972","doi":"https://doi.org/10.52202/079017-0972","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0972","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.23434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Stefan Stojanovic","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Stojanovic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082148015","display_name":"Yassir Jedra","orcid":"https://orcid.org/0000-0002-4403-1066","observed_orcids":["https://orcid.org/0000-0002-4403-1066"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yassir Jedra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025136069","display_name":"Alexandre Prouti\u00e8re","orcid":"https://orcid.org/0000-0002-4679-4673","observed_orcids":["https://orcid.org/0000-0002-4679-4673"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Proutiere","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2887,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5823562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"30886","last_page":"30924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9916999936103821,"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":0.9916999936103821,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.002199999988079071,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0008999999845400453,"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/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/matrix-completion","display_name":"matrix completion","score":0.5989999771118164},{"id":"https://openalex.org/keywords/low-rank-approximation","display_name":"low-rank approximation","score":0.5479999780654907},{"id":"https://openalex.org/keywords/q-value-estimation","display_name":"Q-value estimation","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25360000133514404}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0972","doi":"https://doi.org/10.52202/079017-0972","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0972","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.23434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23434","pdf_url":"https://arxiv.org/pdf/2410.23434","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.2410.23434","doi":"https://doi.org/10.48550/arxiv.2410.23434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.23434","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.23434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23434","pdf_url":"https://arxiv.org/pdf/2410.23434","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":[{"id":"https://openalex.org/G6832510969","display_name":null,"funder_award_id":"KAW 2022","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"}],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415798366.pdf","grobid_xml":"https://content.openalex.org/works/W4415798366.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3100105564","https://openalex.org/W7133243557","https://openalex.org/W4378498853","https://openalex.org/W4377224968","https://openalex.org/W4353007157","https://openalex.org/W4375869306","https://openalex.org/W7222910558","https://openalex.org/W4391383035","https://openalex.org/W4412675958","https://openalex.org/W7133215975"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,39,41,44,49,55,59,66,80,114,137,140,165,173],"problem":[3],"of":[4,54,65,83,139,167],"learning":[5,28],"an":[6,153],"$\\varepsilon$-optimal":[7,154],"policy":[8,32,35,57,155],"in":[9,194],"controlled":[10],"dynamical":[11],"systems":[12],"with":[13],"low-rank":[14,45],"latent":[15],"structure.":[16],"For":[17,121],"this":[18,122,179],"problem,":[19],"we":[20,127],"present":[21],"LoRa-PI":[22,151],"(Low-Rank":[23],"Policy":[24],"Iteration),":[25],"a":[26,77,95,118],"model-free":[27],"algorithm":[29,42,107,177],"alternating":[30],"between":[31],"improvement":[33],"and":[34,86,99,171,184],"evaluation":[36],"steps.":[37],"In":[38],"latter,":[40],"estimates":[43],"matrix":[46,67,115,124,141],"corresponding":[47],"to":[48,74,93,112],"(state,":[50],"action)":[51],"value":[52],"function":[53],"current":[56],"using":[58,117,156],"following":[60],"two-phase":[61],"procedure.":[62],"The":[63,106],"entries":[64,102],"are":[68,90,103],"first":[69],"sampled":[70],"uniformly":[71],"at":[72],"random":[73],"estimate,":[75],"via":[76],"spectral":[78],"method,":[79],"leverage":[81],"scores":[82,89],"its":[84,145],"rows":[85,98],"columns.":[87],"These":[88,147],"then":[91],"used":[92],"extract":[94],"few":[96],"important":[97],"columns":[100],"whose":[101],"further":[104],"sampled.":[105],"exploits":[108],"these":[109],"new":[110],"samples":[111,159],"complete":[113],"estimation":[116,125],"CUR-like":[119],"method.":[120],"leveraged":[123],"procedure,":[126],"establish":[128],"entry-wise":[129],"guarantees":[130,148],"that":[131,150],"remarkably,":[132],"do":[133],"not":[134],"depend":[135],"on":[136,144],"coherence":[138],"but":[142],"only":[143],"spikiness.":[146],"imply":[149],"learns":[152],"$\\widetilde{O}({S+A\\over":[157],"\\mathrm{poly}(1-\u03b3)\\varepsilon^2})$":[158],"where":[160],"$S$":[161],"(resp.":[162,169],"$A$)":[163],"denotes":[164],"number":[166],"states":[168],"actions)":[170],"$\u03b3$":[172],"discount":[174],"factor.":[175],"Our":[176],"achieves":[178],"order-optimal":[180],"(in":[181],"$S$,":[182],"$A$":[183],"$\\varepsilon$)":[185],"sample":[186],"complexity":[187],"under":[188],"milder":[189],"conditions":[190],"than":[191],"those":[192],"assumed":[193],"previously":[195],"proposed":[196],"approaches.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-11-03T00:00:00"}