{"id":"https://openalex.org/W4297580360","doi":"https://doi.org/10.1145/3670686","title":"Tabular and Deep Learning for the Whittle Index","display_name":"Tabular and Deep Learning for the Whittle Index","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4297580360","doi":"https://doi.org/10.1145/3670686"},"language":"en","primary_location":{"id":"doi:10.1145/3670686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3670686","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3670686","source":{"id":"https://openalex.org/S4210231956","display_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","issn_l":"2376-3639","issn":["2376-3639","2376-3647"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3670686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077540864","display_name":"Francisco Robledo","orcid":null},"institutions":[{"id":"https://openalex.org/I144889574","display_name":"Universit\u00e9 de Pau et des Pays de l'Adour","ror":"https://ror.org/01frn9647","country_code":"FR","type":"education","lineage":["https://openalex.org/I144889574"]},{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]},{"id":"https://openalex.org/I4210091673","display_name":"Laboratoire de Math\u00e9matiques et de leurs Applications","ror":"https://ror.org/00g669j87","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I144889574","https://openalex.org/I4210091673","https://openalex.org/I4210141950"]}],"countries":["ES","FR"],"is_corresponding":true,"raw_author_name":"Francisco Robledo Rela\u00f1o","raw_affiliation_strings":["UPV/EHU, Bilbao, Spain and UPPA, Pau France","LMAP - Laboratoire de Math\u00e9matiques et de leurs Applications [Pau] (B\u00e2timent IPRA - Universit\u00e9 de Pau et des Pays de l'Adour Avenue de l'Universit\u00e9 - BP 1155 64013 PAU CEDEX - France)","UPV / EHU - University of the Basque Country = Euskal Herriko Unibertsitatea (Barrio Sarriena s/n, \r\n48940 Leioa, \r\nBizkaia - Spain)"],"raw_orcid":"https://orcid.org/0000-0003-1040-1513","affiliations":[{"raw_affiliation_string":"UPV/EHU, Bilbao, Spain and UPPA, Pau France","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"LMAP - Laboratoire de Math\u00e9matiques et de leurs Applications [Pau] (B\u00e2timent IPRA - Universit\u00e9 de Pau et des Pays de l'Adour Avenue de l'Universit\u00e9 - BP 1155 64013 PAU CEDEX - France)","institution_ids":["https://openalex.org/I144889574","https://openalex.org/I4210091673"]},{"raw_affiliation_string":"UPV / EHU - University of the Basque Country = Euskal Herriko Unibertsitatea (Barrio Sarriena s/n, \r\n48940 Leioa, \r\nBizkaia - Spain)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vivek Borkar","raw_affiliation_strings":["Indian Institute of Technology, Mumbai, India","EE-IIT - Department of Electrical Engineering [IIT-Bombay] (IIT-Bombay, Powai, Mumbai 400 076, India - India)"],"raw_orcid":"https://orcid.org/0000-0003-0756-5402","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"EE-IIT - Department of Electrical Engineering [IIT-Bombay] (IIT-Bombay, Powai, Mumbai 400 076, India - India)","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080096962","display_name":"Urtzi Ayesta","orcid":"https://orcid.org/0000-0003-1761-2313"},"institutions":[{"id":"https://openalex.org/I110594554","display_name":"Ikerbasque","ror":"https://ror.org/01cc3fy72","country_code":"ES","type":"other","lineage":["https://openalex.org/I110594554"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["ES","FR"],"is_corresponding":false,"raw_author_name":"Urtzi Ayesta","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, Toulouse, France, UPV/EHU, Donostia Spain and Ikerbasque, Bilbao, Spain","IRIT-RMESS - R\u00e9seaux, Mobiles, Embarqu\u00e9s, Sans fil, Satellites (Institut de recherche en informatique de Toulouse - IRIT\r\n2 rue Charles Camichel \r\n31071 Toulouse Cedex 7 - France)","CNRS - Centre National de la Recherche Scientifique (France)","Ikerbasque - Basque Foundation for Science (Spain)"],"raw_orcid":"https://orcid.org/0000-0003-1761-2313","affiliations":[{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse, Toulouse, France, UPV/EHU, Donostia Spain and Ikerbasque, Bilbao, Spain","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I110594554"]},{"raw_affiliation_string":"IRIT-RMESS - R\u00e9seaux, Mobiles, Embarqu\u00e9s, Sans fil, Satellites (Institut de recherche en informatique de Toulouse - IRIT\r\n2 rue Charles Camichel \r\n31071 Toulouse Cedex 7 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Ikerbasque - Basque Foundation for Science (Spain)","institution_ids":["https://openalex.org/I110594554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053557735","display_name":"Konstantin Avrachenkov","orcid":"https://orcid.org/0000-0002-8124-8272"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Konstantin Avrachenkov","raw_affiliation_strings":["Inria, Sophia Antipolis, France","NEO  - Network Engineering and Operations (2004 route des Lucioles BP 93 06902 Sophia Antipolis  - France)"],"raw_orcid":"https://orcid.org/0000-0002-8124-8272","affiliations":[{"raw_affiliation_string":"Inria, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"NEO  - Network Engineering and Operations (2004 route des Lucioles BP 93 06902 Sophia Antipolis  - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077540864"],"corresponding_institution_ids":["https://openalex.org/I144889574","https://openalex.org/I169108374","https://openalex.org/I4210091673"],"apc_list":null,"apc_paid":null,"fwci":2.68,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89339586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"9","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.9904999732971191,"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":0.658959686756134},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5258046984672546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5123225450515747},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4917495548725128},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47193643450737},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.467556357383728},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4568652808666229},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.44617539644241333},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4340580701828003},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.43051695823669434},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4280624985694885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4077211618423462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.336584210395813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3353835940361023},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06723836064338684}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.658959686756134},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5258046984672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5123225450515747},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4917495548725128},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47193643450737},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.467556357383728},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4568652808666229},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.44617539644241333},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4340580701828003},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43051695823669434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4280624985694885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4077211618423462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336584210395813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3353835940361023},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06723836064338684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3670686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3670686","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3670686","source":{"id":"https://openalex.org/S4210231956","display_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","issn_l":"2376-3639","issn":["2376-3639","2376-3647"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2406.02057","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.02057","pdf_url":"https://arxiv.org/pdf/2406.02057","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":"pmh:oai:HAL:hal-03767324v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03767324","pdf_url":"https://hal.science/hal-03767324/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"https://ewrl.wordpress.com/ewrl15-2022/","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-03810695v1","is_oa":true,"landing_page_url":"https://hal-univ-pau.archives-ouvertes.fr/hal-03810695","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EWRL 2022 - 15th European Workshop on Reinforcement Learning","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-04599291v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04599291","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems, 2024, &#x27E8;10.1145/3670686&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1145/3670686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3670686","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3670686","source":{"id":"https://openalex.org/S4210231956","display_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","issn_l":"2376-3639","issn":["2376-3639","2376-3647"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G5482886782","display_name":null,"funder_award_id":"ANR-22-CE25-0013-02 (ANR EPLER)","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8896920958","display_name":null,"funder_award_id":"IT1456-22","funder_id":"https://openalex.org/F4320321705","funder_display_name":"Eusko Jaurlaritza"},{"id":"https://openalex.org/G8915466891","display_name":"Efficient Planning and Learning for Resource Sharing","funder_award_id":"ANR-22-CE25-0013","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"},{"id":"https://openalex.org/F4320320721","display_name":"Council of Scientific and Industrial Research, India","ror":"https://ror.org/021wm7p51"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297580360.pdf","grobid_xml":"https://content.openalex.org/works/W4297580360.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W146031494","https://openalex.org/W2044502527","https://openalex.org/W2056921512","https://openalex.org/W2105556121","https://openalex.org/W2141515329","https://openalex.org/W2145339207","https://openalex.org/W2149943599","https://openalex.org/W2154204727","https://openalex.org/W2184204218","https://openalex.org/W2499002200","https://openalex.org/W2511028367","https://openalex.org/W2746553466","https://openalex.org/W2793205632","https://openalex.org/W2800455436","https://openalex.org/W2963782453","https://openalex.org/W2982074554","https://openalex.org/W2997055691","https://openalex.org/W3022217175","https://openalex.org/W3104937890","https://openalex.org/W3171374485","https://openalex.org/W4206435191","https://openalex.org/W4214717370","https://openalex.org/W4233840023","https://openalex.org/W4243772471"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"The":[0,57],"Whittle":[1,50,83,103],"index":[2,51],"policy":[3],"is":[4,60,95,127,161],"a":[5,66,76,96],"heuristic":[6],"that":[7,92,148,174],"has":[8],"shown":[9],"remarkably":[10],"good":[11],"performance":[12],"(with":[13],"guaranteed":[14],"asymptotic":[15],"optimality)":[16],"when":[17],"applied":[18],"to":[19,47,69,80,100,117,129,135,140],"the":[20,49,53,61,71,82,101,119,123,153,162,181],"class":[21],"of":[22,63,111,152,165],"problems":[23],"known":[24],"as":[25],"Restless":[26],"Multi-Armed":[27],"Bandit":[28],"Problems":[29],"(RMABPs).":[30],"In":[31,85],"this":[32],"article,":[33],"we":[34,90,146],"present":[35,107],"QWI":[36,112,175],"and":[37,45,75,137,176,190],"QWINN,":[38,108,145],"two":[39,64],"reinforcement":[40],"learning":[41],"algorithms,":[42],"respectively":[43],"tabular":[44,97],"deep,":[46],"learn":[48],"for":[52,168],"total":[54],"discounted":[55],"criterion.":[56],"key":[58],"feature":[59],"use":[62],"time-scales,":[65],"faster":[67,124,179],"one":[68,79,133],"update":[70,81],"state-action":[72],"Q":[73,120,183],"-values,":[74],"relatively":[77],"slower":[78],"indices.":[84,104],"our":[86],"main":[87],"theoretical":[88],"result,":[89],"show":[91,147,173],"QWI,":[93],"which":[94,126,160],"implementation,":[98],"converges":[99],"real":[102],"We":[105],"then":[106],"an":[109],"adaptation":[110],"algorithm":[113],"using":[114],"neural":[115],"networks":[116],"compute":[118],"-values":[121],"on":[122],"time-scale,":[125],"able":[128],"extrapolate":[130],"information":[131],"from":[132],"state":[134],"another":[136],"scales":[138],"naturally":[139],"large":[141],"state-space":[142],"environments.":[143],"For":[144],"all":[149],"local":[150],"minima":[151],"Bellman":[154],"error":[155],"are":[156],"locally":[157],"stable":[158],"equilibria,":[159],"first":[163],"result":[164],"its":[166],"kind":[167],"DQN-based":[169],"schemes.":[170],"Numerical":[171],"computations":[172],"QWINN":[177],"converge":[178],"than":[180],"standard":[182],"-learning":[184],"algorithm,":[185],"neural-network":[186],"based":[187],"approximate":[188],"Q-learning,":[189],"other":[191],"state-of-the-art":[192],"algorithms.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-09-30T00:00:00"}
