{"id":"https://openalex.org/W4392902809","doi":"https://doi.org/10.1109/icassp48485.2024.10448465","title":"Tensor Low-Rank Approximation of Finite-Horizon Value Functions","display_name":"Tensor Low-Rank Approximation of Finite-Horizon Value Functions","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902809","doi":"https://doi.org/10.1109/icassp48485.2024.10448465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448465","doi":"https://doi.org/10.1109/icassp48485.2024.10448465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448465","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2405.17628","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077468628","display_name":"Sergio Rozada","orcid":"https://orcid.org/0000-0003-1042-7502","observed_orcids":["https://orcid.org/0000-0003-1042-7502"]},"institutions":[{"id":"https://openalex.org/I182083151","display_name":"Universidad Rey Juan Carlos","ror":"https://ror.org/01v5cv687","country_code":"ES","type":"education","lineage":["https://openalex.org/I182083151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio Rozada","raw_affiliation_strings":["King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain","Dept. of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain","institution_ids":["https://openalex.org/I182083151"]},{"raw_affiliation_string":"Dept. of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain","institution_ids":["https://openalex.org/I182083151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054312245","display_name":"Antonio Garcia Marques","orcid":"https://orcid.org/0000-0002-4642-7718","observed_orcids":["https://orcid.org/0000-0002-4642-7718"]},"institutions":[{"id":"https://openalex.org/I182083151","display_name":"Universidad Rey Juan Carlos","ror":"https://ror.org/01v5cv687","country_code":"ES","type":"education","lineage":["https://openalex.org/I182083151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio G. Marques","raw_affiliation_strings":["King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain","Dept. of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain","institution_ids":["https://openalex.org/I182083151"]},{"raw_affiliation_string":"Dept. of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain","institution_ids":["https://openalex.org/I182083151"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I182083151"],"apc_list":null,"apc_paid":null,"fwci":0.6314,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69506621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5975","last_page":"5979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5673999786376953,"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":0.5673999786376953,"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/T12303","display_name":"Tensor decomposition and applications","score":0.4097000062465668,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/finite-horizon-markov-decision-processes","display_name":"finite-horizon Markov decision processes","score":0.9430000185966492},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7950000166893005},{"id":"https://openalex.org/keywords/low-rank-tensor-approximation","display_name":"low-rank tensor approximation","score":0.703000009059906},{"id":"https://openalex.org/keywords/parafac-decomposition","display_name":"PARAFAC decomposition","score":0.9900000095367432},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7250000238418579},{"id":"https://openalex.org/keywords/nonparametric-estimation","display_name":"nonparametric estimation","score":0.6809999942779541}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7999095320701599},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6564978361129761},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6253572106361389},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5744413733482361},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.567295491695404},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5400382876396179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47022318840026855},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4552116096019745},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.444572776556015},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.414799302816391},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38870981335639954},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3840256631374359},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36419394612312317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.176947683095932},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.092212975025177},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08485537767410278},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448465","doi":"https://doi.org/10.1109/icassp48485.2024.10448465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448465","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.17628","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.17628","pdf_url":"https://arxiv.org/pdf/2405.17628","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.17628","doi":"https://doi.org/10.48550/arxiv.2405.17628","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.17628","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:2405.17628","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.17628","pdf_url":"https://arxiv.org/pdf/2405.17628","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1175115578","display_name":null,"funder_award_id":"AEI//10.13039/501100011033/","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2409277324","display_name":null,"funder_award_id":"TED2021-130347B-I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G300979063","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3802065679","display_name":null,"funder_award_id":"PID2019- 105032GB-I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G425668148","display_name":null,"funder_award_id":".13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G800634236","display_name":null,"funder_award_id":"PID2022\u2010136887NB\u2010I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8684520763","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":"https://ror.org/003x0zc53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392902809.pdf","grobid_xml":"https://content.openalex.org/works/W4392902809.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1915973093","https://openalex.org/W1964375638","https://openalex.org/W1999912147","https://openalex.org/W2024165284","https://openalex.org/W2078677240","https://openalex.org/W2119741678","https://openalex.org/W2145339207","https://openalex.org/W2282722544","https://openalex.org/W2469230926","https://openalex.org/W2586680856","https://openalex.org/W2903857590","https://openalex.org/W2975296231","https://openalex.org/W2998461398","https://openalex.org/W3100105564","https://openalex.org/W3128969903","https://openalex.org/W3156706052","https://openalex.org/W3157945851","https://openalex.org/W4205326910","https://openalex.org/W4286892941","https://openalex.org/W4298023569","https://openalex.org/W4392979614"],"related_works":["https://openalex.org/W4392979614","https://openalex.org/W4406692412","https://openalex.org/W3157945851","https://openalex.org/W4416582662","https://openalex.org/W4382199092","https://openalex.org/W2203207606","https://openalex.org/W4375869306","https://openalex.org/W4412675958","https://openalex.org/W2226967293","https://openalex.org/W7169969209"],"abstract_inverted_index":{"The":[0,169],"goal":[1],"of":[2,19,79,89,111,130,164,167,171,182],"reinforcement":[3],"learning":[4],"is":[5,26,128],"estimating":[6,30],"a":[7,20,74,102,121],"policy":[8],"that":[9,160],"maps":[10],"states":[11],"to":[12,81,107,141,154,180],"actions":[13],"and":[14,53],"maximizes":[15],"the":[16,32,44,50,64,67,77,87,90,96,109,117,131,139,143,150,162,165,172],"cumulative":[17],"reward":[18],"Markov":[21],"Decision":[22],"Process":[23],"(MDP).":[24],"This":[25,72,99],"oftentimes":[27],"achieved":[28],"by":[29],"first":[31],"optimal":[33,51,144],"(reward)":[34],"value":[35],"function":[36],"(VF)":[37],"associated":[38],"with":[39,70,86,95,178],"each":[40,181],"state-action":[41,91],"pair.":[42],"When":[43],"MDP":[45,140],"has":[46],"an":[47,156],"infinite":[48],"horizon,":[49],"VFs":[52,65,80,110,119],"policies":[54],"are":[55],"stationary":[56],"under":[57],"mild":[58],"conditions.":[59],"However,":[60],"in":[61],"finite-horizon":[62,112],"MDPs,":[63],"(hence,":[66],"policies)":[68],"vary":[69],"time.":[71],"poses":[73],"challenge":[75],"since":[76],"number":[78],"estimate":[82,142],"grows":[83,176],"not":[84],"only":[85],"size":[88,170],"space":[92],"but":[93],"also":[94],"time":[97,127],"horizon.":[98],"paper":[100],"proposes":[101],"non-parametric":[103],"low-rank":[104,158,173],"stochastic":[105],"algorithm":[106,159],"approximate":[108],"MDPs.":[113],"First,":[114],"we":[115,134,148],"represent":[116],"(unknown)":[118],"as":[120,189],"multi-dimensional":[122],"array,":[123],"or":[124],"tensor,":[125],"where":[126],"one":[129],"dimensions.":[132],"Then,":[133],"use":[135,149],"rewards":[136],"sampled":[137],"from":[138],"VFs.":[145,168],"More":[146],"precisely,":[147],"(truncated)":[151],"PARAFAC":[152,174],"decomposition":[153],"design":[155],"online":[157],"recovers":[161],"entries":[163],"tensor":[166],"model":[175],"additively":[177],"respect":[179],"its":[183],"dimensions,":[184],"rendering":[185],"our":[186],"approach":[187],"efficient,":[188],"demonstrated":[190],"via":[191],"numerical":[192],"experiments.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2024-03-19T00:00:00"}