{"id":"https://openalex.org/W4206435191","doi":"https://doi.org/10.1007/978-3-030-92511-6_10","title":"A Novel Implementation of\u00a0Q-Learning for\u00a0the\u00a0Whittle Index","display_name":"A Novel Implementation of\u00a0Q-Learning for\u00a0the\u00a0Whittle Index","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4206435191","doi":"https://doi.org/10.1007/978-3-030-92511-6_10"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-92511-6_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-92511-6_10","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"},"type":"book-chapter","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/A5043307603","display_name":"Lachlan J. Gibson","orcid":"https://orcid.org/0000-0001-7345-7878"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Lachlan J. Gibson","raw_affiliation_strings":["School of Mathematics and Physics, The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010128000","display_name":"Peter Jacko","orcid":"https://orcid.org/0000-0003-3376-0260"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Jacko","raw_affiliation_strings":["Berry Consultants, Abingdon, UK","Lancaster University, Lancaster, UK"],"affiliations":[{"raw_affiliation_string":"Berry Consultants, Abingdon, UK","institution_ids":[]},{"raw_affiliation_string":"Lancaster University, Lancaster, UK","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070445330","display_name":"Yoni Nazarathy","orcid":"https://orcid.org/0000-0003-3071-8462"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yoni Nazarathy","raw_affiliation_strings":["School of Mathematics and Physics, The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043307603"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":2.4235,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91252877,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T11182","display_name":"Auction Theory and Applications","score":0.9922999739646912,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9832000136375427,"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":0.7887279987335205},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7494485378265381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6540126204490662},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.633213996887207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6287919282913208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5438143014907837},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4632379412651062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40550506114959717},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39144888520240784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19739139080047607}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7887279987335205},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7494485378265381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540126204490662},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.633213996887207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6287919282913208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5438143014907837},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4632379412651062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40550506114959717},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39144888520240784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19739139080047607},{"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-92511-6_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-92511-6_10","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"},{"id":"pmh:oai:eprints.lancs.ac.uk:166601","is_oa":false,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/166601/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Contribution in Book/Report/Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1537383030","https://openalex.org/W1916369423","https://openalex.org/W1983962754","https://openalex.org/W1996475996","https://openalex.org/W1998376807","https://openalex.org/W2013702609","https://openalex.org/W2022063709","https://openalex.org/W2044206847","https://openalex.org/W2044502527","https://openalex.org/W2056921512","https://openalex.org/W2105556121","https://openalex.org/W2111983268","https://openalex.org/W2115138651","https://openalex.org/W2119217665","https://openalex.org/W2132651882","https://openalex.org/W2135063910","https://openalex.org/W2149590435","https://openalex.org/W2149721706","https://openalex.org/W2154204727","https://openalex.org/W2172140255","https://openalex.org/W2178643644","https://openalex.org/W2255981264","https://openalex.org/W2467243923","https://openalex.org/W2499002200","https://openalex.org/W2511028367","https://openalex.org/W2912380945","https://openalex.org/W2964144046","https://openalex.org/W2997055691","https://openalex.org/W3022217175","https://openalex.org/W3103744592","https://openalex.org/W3104937890","https://openalex.org/W3125634603","https://openalex.org/W4214717370","https://openalex.org/W4246270964","https://openalex.org/W4254113915"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
