{"id":"https://openalex.org/W3157945851","doi":"https://doi.org/10.23919/eusipco54536.2021.9616008","title":"Low-rank State-action Value-function Approximation","display_name":"Low-rank State-action Value-function Approximation","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3157945851","doi":"https://doi.org/10.23919/eusipco54536.2021.9616008","mag":"3157945851"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616008","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616008","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.08805","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"},"institutions":[{"id":"https://openalex.org/I133498377","display_name":"Banco Bilbao Vizcaya Argentaria (Spain)","ror":"https://ror.org/0537dnd74","country_code":"ES","type":"company","lineage":["https://openalex.org/I133498377"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sergio Rozada","raw_affiliation_strings":["Clients Solutions Advanced Analytics, BBVA, Madrid, Spain","Dept. of Signal Theory and Comms., URJC, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Clients Solutions Advanced Analytics, BBVA, Madrid, Spain","institution_ids":["https://openalex.org/I133498377"]},{"raw_affiliation_string":"Dept. of Signal Theory and Comms., URJC, Madrid, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075337854","display_name":"V\u00edctor M. Tenorio","orcid":"https://orcid.org/0000-0002-0079-7326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Tenorio","raw_affiliation_strings":["URJC,Dept. of Signal Theory and Comms.,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"URJC,Dept. of Signal Theory and Comms.,Madrid,Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054312245","display_name":"Antonio G. Marqu\u00e9s","orcid":"https://orcid.org/0000-0002-4642-7718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio G. Marques","raw_affiliation_strings":["URJC,Dept. of Signal Theory and Comms.,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"URJC,Dept. of Signal Theory and Comms.,Madrid,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077468628"],"corresponding_institution_ids":["https://openalex.org/I133498377"],"apc_list":null,"apc_paid":null,"fwci":0.150358,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5522279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1471","last_page":"1475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6671457290649414},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6585452556610107},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6234198808670044},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.593881368637085},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.573444664478302},{"id":"https://openalex.org/keywords/low-rank-approximation","display_name":"Low-rank approximation","score":0.5641188621520996},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5412885546684265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48972347378730774},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.47759366035461426},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4757877588272095},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4517839848995209},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43176013231277466},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42105960845947266},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.41443681716918945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39879897236824036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3370669484138489},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31586888432502747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3135499060153961},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09242132306098938}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6671457290649414},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6585452556610107},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6234198808670044},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.593881368637085},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.573444664478302},{"id":"https://openalex.org/C90199385","wikidata":"https://www.wikidata.org/wiki/Q6692777","display_name":"Low-rank approximation","level":3,"score":0.5641188621520996},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5412885546684265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48972347378730774},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.47759366035461426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4757877588272095},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4517839848995209},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43176013231277466},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42105960845947266},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41443681716918945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39879897236824036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3370669484138489},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31586888432502747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3135499060153961},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09242132306098938},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C25023664","wikidata":"https://www.wikidata.org/wiki/Q1575637","display_name":"Hankel matrix","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616008","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616008","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.08805","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.08805","pdf_url":"https://arxiv.org/pdf/2104.08805","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3157945851","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2104.08805","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.08805","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.08805","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.08805","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.08805","pdf_url":"https://arxiv.org/pdf/2104.08805","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320324496","display_name":"Universidad Rey Juan Carlos","ror":"https://ror.org/01v5cv687"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157945851.pdf","grobid_xml":"https://content.openalex.org/works/W3157945851.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1757796397","https://openalex.org/W2004026774","https://openalex.org/W2121863487","https://openalex.org/W2130304665","https://openalex.org/W2138505091","https://openalex.org/W2150226602","https://openalex.org/W2164616133","https://openalex.org/W2203207606","https://openalex.org/W2500090022","https://openalex.org/W2510855940","https://openalex.org/W2545659366","https://openalex.org/W2568999269","https://openalex.org/W2625214068","https://openalex.org/W2785403755","https://openalex.org/W2963886613","https://openalex.org/W2966367827","https://openalex.org/W2975296231","https://openalex.org/W2987046690","https://openalex.org/W3035067130","https://openalex.org/W3099134564","https://openalex.org/W4206519735","https://openalex.org/W4246706978","https://openalex.org/W6637967152","https://openalex.org/W6688047613","https://openalex.org/W6729229454","https://openalex.org/W6747775657","https://openalex.org/W6768377102","https://openalex.org/W6779832840","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1887316253","https://openalex.org/W2767700711","https://openalex.org/W2487200711","https://openalex.org/W2261430036","https://openalex.org/W2791099456","https://openalex.org/W2952364022","https://openalex.org/W2261141559","https://openalex.org/W2994974560","https://openalex.org/W2617695214","https://openalex.org/W2064951599","https://openalex.org/W1959879694","https://openalex.org/W2750224119","https://openalex.org/W3016957078","https://openalex.org/W2891721757","https://openalex.org/W2770109286","https://openalex.org/W1680800188","https://openalex.org/W2931189561","https://openalex.org/W2808355480","https://openalex.org/W2762617730","https://openalex.org/W2936067989"],"abstract_inverted_index":{"Value":[0],"functions":[1],"are":[2],"central":[3],"to":[4,34,46,90,105,117],"Dynamic":[5],"Programming":[6],"and":[7,51,78,113],"Reinforcement":[8],"Learning":[9],"but":[10],"their":[11],"exact":[12],"estimation":[13,27],"suffers":[14],"from":[15,38,81],"the":[16,21,96,111],"curse":[17],"of":[18,23,49,95],"dimensionality,":[19],"challenging":[20],"development":[22],"practical":[24],"value-function":[25],"(VF)":[26],"algorithms.":[28],"Several":[29],"approaches":[30],"have":[31],"been":[32],"proposed":[33],"overcome":[35],"this":[36,77,84],"issue,":[37],"non-parametric":[39,103],"schemes":[40],"that":[41,108,121],"aggregate":[42],"states":[43],"or":[44,58],"actions":[45],"parametric":[47],"approximations":[48],"state":[50,65],"action":[52],"VFs":[53],"via,":[54],"e.g.,":[55],"linear":[56],"estimators":[57],"deep":[59],"neural":[60],"networks.":[61],"Relevantly,":[62],"several":[63],"high-dimensional":[64],"problems":[66],"can":[67],"be":[68],"well-approximated":[69],"by":[70,76],"an":[71],"intrinsic":[72],"low-rank":[73,82,93],"structure.":[74],"Motivated":[75],"leveraging":[79],"results":[80],"optimization,":[83],"paper":[85],"proposes":[86],"different":[87],"stochastic":[88],"algorithms":[89],"estimate":[91,122],"a":[92,102],"factorization":[94],"$Q(s,":[97],"a)$":[98],"matrix.":[99],"This":[100],"is":[101],"alternative":[104],"VF":[106],"approximation":[107],"dramatically":[109],"reduces":[110],"computational":[112],"sample":[114],"complexities":[115],"relative":[116],"classical":[118],"$Q$-learning":[119],"methods":[120],"$Q(s,a)$":[123],"separately":[124],"for":[125],"each":[126],"state-action":[127],"pair.":[128]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}