{"id":"https://openalex.org/W3114411349","doi":"https://doi.org/10.1109/wsc48552.2020.9384078","title":"Deep Reinforcement Learning in Linear Discrete Action Spaces","display_name":"Deep Reinforcement Learning in Linear Discrete Action Spaces","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3114411349","doi":"https://doi.org/10.1109/wsc48552.2020.9384078","mag":"3114411349"},"language":"en","primary_location":{"id":"doi:10.1109/wsc48552.2020.9384078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc48552.2020.9384078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/32908/32908.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043700615","display_name":"Wouter van Heeswijk","orcid":"https://orcid.org/0000-0002-5413-9660"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Wouter van Heeswijk","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, THE NETHERLANDS"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, THE NETHERLANDS","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064781958","display_name":"Han La Poutr\u00e9","orcid":"https://orcid.org/0009-0005-6767-4688"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Han La Poutre","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, THE NETHERLANDS"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, THE NETHERLANDS","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043700615"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":null,"apc_paid":null,"fwci":0.2975,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.582222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"521","issue":null,"first_page":"1063","last_page":"1074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9907000064849854,"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"}},{"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"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8007034063339233},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.635863721370697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6024785041809082},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5498924851417542},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.5277013778686523},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5247424244880676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4587554931640625},{"id":"https://openalex.org/keywords/network-planning-and-design","display_name":"Network planning and design","score":0.4108123779296875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3771951496601105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2717210054397583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8007034063339233},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.635863721370697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6024785041809082},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5498924851417542},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5277013778686523},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5247424244880676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4587554931640625},{"id":"https://openalex.org/C114563136","wikidata":"https://www.wikidata.org/wiki/Q19725982","display_name":"Network planning and design","level":2,"score":0.4108123779296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3771951496601105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2717210054397583},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wsc48552.2020.9384078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc48552.2020.9384078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:cwi.nl:32908","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/32908","pdf_url":"https://ir.cwi.nl/pub/32908/32908.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:cwi:oai:cwi.nl:30754","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/30754","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"pmh:ut:oai:ris.utwente.nl:publications/7d369cdd-6864-4d8f-b4b9-901792f8997a","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/deep-reinforcement-learning-in-linear-discrete-action-spaces(7d369cdd-6864-4d8f-b4b9-901792f8997a).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2020 Winter Simulation Conference","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:cwi.nl:32908","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/32908","pdf_url":"https://ir.cwi.nl/pub/32908/32908.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114411349.pdf","grobid_xml":"https://content.openalex.org/works/W3114411349.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1569512666","https://openalex.org/W1569658069","https://openalex.org/W1626155273","https://openalex.org/W1677182931","https://openalex.org/W1696538018","https://openalex.org/W1745373831","https://openalex.org/W1941445455","https://openalex.org/W2011233848","https://openalex.org/W2044287460","https://openalex.org/W2056653303","https://openalex.org/W2062457326","https://openalex.org/W2076063813","https://openalex.org/W2098432798","https://openalex.org/W2109634117","https://openalex.org/W2141473882","https://openalex.org/W2173248099","https://openalex.org/W2183243664","https://openalex.org/W2215378786","https://openalex.org/W2331143823","https://openalex.org/W2356798126","https://openalex.org/W2511261638","https://openalex.org/W2616463902","https://openalex.org/W2741534749","https://openalex.org/W2801079363","https://openalex.org/W2909736260","https://openalex.org/W2919115771","https://openalex.org/W2949892913","https://openalex.org/W2950183737","https://openalex.org/W2963864421","https://openalex.org/W3105432754","https://openalex.org/W3150570724","https://openalex.org/W4289420954","https://openalex.org/W4394672593","https://openalex.org/W6680850120","https://openalex.org/W6684921986","https://openalex.org/W6685951826","https://openalex.org/W6706493343","https://openalex.org/W6737988291","https://openalex.org/W6751044371"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Problems":[0],"in":[1],"operations":[2],"research":[3],"are":[4],"typically":[5],"combinatorial":[6],"and":[7,86,146],"high-dimensional.":[8],"To":[9],"a":[10,27,77,118,127],"degree,":[11],"linear":[12,56,84,99,115],"programs":[13],"may":[14],"efficiently":[15],"solve":[16],"such":[17,52,72],"large":[18],"decision":[19,100],"problems.":[20],"For":[21],"stochastic":[22],"multi-period":[23],"problems,":[24,75,101],"decomposition":[25],"into":[26,54,97],"sequence":[28],"of":[29,107,113,120],"one-stage":[30,55,98],"decisions":[31],"with":[32,110,143],"approximated":[33],"downstream":[34],"effects":[35],"is":[36,60],"often":[37],"necessary,":[38],"e.g.,":[39],"by":[40,62],"deploying":[41],"reinforcement":[42,79],"learning":[43,80],"to":[44],"obtain":[45],"value":[46],"function":[47],"approximations":[48],"(VFAs).":[49],"When":[50],"embedding":[51],"VFAs":[53,96,133,137],"programs,":[57],"VFA":[58],"design":[59,145],"restricted":[61],"linearity.":[63],"This":[64],"paper":[65],"presents":[66],"an":[67],"integrated":[68],"simulation":[69],"approach":[70],"for":[71],"complex":[73],"optimization":[74],"developing":[76],"deep":[78],"algorithm":[81],"that":[82],"combines":[83],"programming":[85],"neural":[87,94,108,131],"network":[88,95,132],"VFAs.":[89],"Our":[90],"proposed":[91],"method":[92],"embeds":[93],"combining":[102],"the":[103,111],"nonlinear":[104],"expressive":[105],"power":[106],"networks":[109],"efficiency":[112],"solving":[114],"programs.":[116],"As":[117],"proof":[119],"concept,":[121],"we":[122],"perform":[123],"numerical":[124],"experiments":[125],"on":[126],"transportation":[128],"problem.":[129],"The":[130],"consistently":[134],"outperform":[135],"polynomial":[136],"as":[138,140],"well":[139],"other":[141],"benchmarks,":[142],"limited":[144],"tuning":[147],"effort.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}