{"id":"https://openalex.org/W4392979614","doi":"https://doi.org/10.1109/tsp.2024.3379089","title":"Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning","display_name":"Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392979614","doi":"https://doi.org/10.1109/tsp.2024.3379089"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2024.3379089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2024.3379089","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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/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":true,"raw_author_name":"Sergio Rozada","raw_affiliation_strings":["Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain","institution_ids":["https://openalex.org/I182083151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001418995","display_name":"Santiago Paternain","orcid":"https://orcid.org/0000-0001-6310-6345"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santiago Paternain","raw_affiliation_strings":["Department of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Institute, Troy, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Institute, Troy, MI, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054312245","display_name":"Antonio G. Marqu\u00e9s","orcid":"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":["Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain","institution_ids":["https://openalex.org/I182083151"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077468628"],"corresponding_institution_ids":["https://openalex.org/I182083151"],"apc_list":null,"apc_paid":null,"fwci":3.2733,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92567501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"72","issue":null,"first_page":"1634","last_page":"1649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9071000218391418,"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":0.9071000218391418,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5395731925964355},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5121371746063232},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48637035489082336},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4644242823123932},{"id":"https://openalex.org/keywords/low-rank-approximation","display_name":"Low-rank approximation","score":0.45913106203079224},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.45737695693969727},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41956549882888794},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40299931168556213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3694952726364136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36620742082595825},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3211713433265686},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2311357855796814},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.1747840940952301}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5395731925964355},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5121371746063232},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48637035489082336},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4644242823123932},{"id":"https://openalex.org/C90199385","wikidata":"https://www.wikidata.org/wiki/Q6692777","display_name":"Low-rank approximation","level":3,"score":0.45913106203079224},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.45737695693969727},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41956549882888794},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40299931168556213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3694952726364136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36620742082595825},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3211713433265686},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2311357855796814},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.1747840940952301},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2024.3379089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2024.3379089","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1492459858","https://openalex.org/W2004026774","https://openalex.org/W2024165284","https://openalex.org/W2061508005","https://openalex.org/W2098432798","https://openalex.org/W2103972604","https://openalex.org/W2119741678","https://openalex.org/W2130304665","https://openalex.org/W2134332047","https://openalex.org/W2138505091","https://openalex.org/W2145339207","https://openalex.org/W2150226602","https://openalex.org/W2201581102","https://openalex.org/W2203207606","https://openalex.org/W2258054274","https://openalex.org/W2469230926","https://openalex.org/W2500090022","https://openalex.org/W2510855940","https://openalex.org/W2568999269","https://openalex.org/W2625214068","https://openalex.org/W2766447205","https://openalex.org/W2786320458","https://openalex.org/W2950226226","https://openalex.org/W2952198983","https://openalex.org/W2963886613","https://openalex.org/W2966367827","https://openalex.org/W2975296231","https://openalex.org/W3128969903","https://openalex.org/W3207166640","https://openalex.org/W3208809545","https://openalex.org/W4205326910","https://openalex.org/W4206331184","https://openalex.org/W4206519735","https://openalex.org/W4211171425","https://openalex.org/W4214717370","https://openalex.org/W4286892402","https://openalex.org/W4298857966","https://openalex.org/W4377224968","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6688047613","https://openalex.org/W6693997783","https://openalex.org/W6729203000","https://openalex.org/W6729229454","https://openalex.org/W6739917199","https://openalex.org/W6747775657","https://openalex.org/W6748324931","https://openalex.org/W6768377102","https://openalex.org/W6778883912","https://openalex.org/W6779222922","https://openalex.org/W6779832840","https://openalex.org/W6780559895","https://openalex.org/W6796664490","https://openalex.org/W6803413346","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2781510240","https://openalex.org/W2170114491","https://openalex.org/W2950186459","https://openalex.org/W2569661359","https://openalex.org/W2242624680","https://openalex.org/W2136127937","https://openalex.org/W2897298721","https://openalex.org/W4290987221","https://openalex.org/W2216309014","https://openalex.org/W3199841771"],"abstract_inverted_index":{"Value":[0],"function":[1],"(VF)":[2],"approximation":[3],"is":[4,122,127],"a":[5,23,53,94],"central":[6],"problem":[7],"in":[8,34,72],"reinforcement":[9],"learning":[10],"(RL).":[11],"Classical":[12],"non-parametric":[13],"VF":[14,70,90],"estimation":[15],"suffers":[16],"from":[17],"the":[18,69,88,102,116],"curse":[19],"of":[20,115],"dimensionality.":[21],"As":[22],"result,":[24],"parsimonious":[25],"parametric":[26],"models":[27],"have":[28],"been":[29],"adopted":[30],"to":[31,67,82,105],"approximate":[32],"VFs":[33,80],"high-dimensional":[35],"spaces,":[36],"with":[37,93],"most":[38],"efforts":[39],"being":[40],"focused":[41],"on":[42],"linear":[43],"and":[44,75,99,124],"neural":[45],"network-based":[46],"approaches.":[47],"Differently,":[48],"this":[49],"paper":[50],"puts":[51],"forth":[52],"<italic":[54,62],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">parsimonious":[56],"non-parametric</i>":[57],"approach,":[58],"where":[59],"we":[60,85],"use":[61],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">stochastic":[64],"low-rank":[65,111],"algorithms</i>":[66],"estimate":[68],"matrix":[71,91],"an":[73,107],"online":[74,108],"model-free":[76,109],"fashion.":[77],"Furthermore,":[78],"as":[79],"tend":[81],"be":[83],"multi-dimensional,":[84],"propose":[86],"replacing":[87],"classical":[89],"representation":[92],"tensor":[95,110],"(multi-way":[96],"array)":[97],"representation,":[98],"then":[100],"using":[101,130],"PARAFAC":[103],"decomposition":[104],"design":[106],"algorithm.":[112],"Different":[113],"versions":[114],"algorithms":[117],"are":[118],"proposed,":[119],"their":[120,125],"complexity":[121],"analyzed,":[123],"performance":[126],"assessed":[128],"numerically":[129],"standardized":[131],"RL":[132],"environments.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}