{"id":"https://openalex.org/W4318603635","doi":"https://doi.org/10.1109/ssci51031.2022.10022256","title":"A Deep Reinforcement Learning Approach for Inventory Control under Stochastic Lead Time and Demand","display_name":"A Deep Reinforcement Learning Approach for Inventory Control under Stochastic Lead Time and Demand","publication_year":2022,"publication_date":"2022-12-04","ids":{"openalex":"https://openalex.org/W4318603635","doi":"https://doi.org/10.1109/ssci51031.2022.10022256"},"language":"en","primary_location":{"id":"doi:10.1109/ssci51031.2022.10022256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci51031.2022.10022256","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-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/A5022828186","display_name":"Manoj Shakya","orcid":"https://orcid.org/0000-0001-9879-2613"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Manoj Shakya","raw_affiliation_strings":["School of Computer Science and Engineering Nanyang Technological University,Singapore","School of Computer Science and Engineering Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062087243","display_name":"Bu\u2010Sung Lee","orcid":"https://orcid.org/0000-0001-7828-7900"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bu-Sung Lee","raw_affiliation_strings":["School of Computer Science and Engineering Nanyang Technological University,Singapore","School of Computer Science and Engineering Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034681806","display_name":"Huey Yuen Ng","orcid":"https://orcid.org/0000-0001-8848-6428"},"institutions":[{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huey Yuen Ng","raw_affiliation_strings":["Singapore Institute of Manufacturing Technology,Singapore","Singapore Institute of Manufacturing Technology, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Institute of Manufacturing Technology,Singapore","institution_ids":["https://openalex.org/I4210091207"]},{"raw_affiliation_string":"Singapore Institute of Manufacturing Technology, Singapore","institution_ids":["https://openalex.org/I4210091207"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022828186"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":4.5903,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.965412,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"760","last_page":"766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9961000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9168000221252441,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9223752021789551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7709083557128906},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7481235861778259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950795650482178},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.674493670463562},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6282920241355896},{"id":"https://openalex.org/keywords/lead-time","display_name":"Lead time","score":0.5405600666999817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4727773666381836},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4549245238304138},{"id":"https://openalex.org/keywords/lost-sales","display_name":"Lost sales","score":0.44407007098197937},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41098666191101074},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.34962165355682373},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.28814440965652466},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15213048458099365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11322125792503357},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.0936640202999115}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9223752021789551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7709083557128906},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7481235861778259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950795650482178},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.674493670463562},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6282920241355896},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.5405600666999817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4727773666381836},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4549245238304138},{"id":"https://openalex.org/C2781161759","wikidata":"https://www.wikidata.org/wiki/Q24451192","display_name":"Lost sales","level":2,"score":0.44407007098197937},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41098666191101074},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.34962165355682373},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28814440965652466},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15213048458099365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11322125792503357},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0936640202999115},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci51031.2022.10022256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci51031.2022.10022256","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1990995139","https://openalex.org/W1995721528","https://openalex.org/W2070410573","https://openalex.org/W2491057494","https://openalex.org/W2752539101","https://openalex.org/W2963416809","https://openalex.org/W3005588823","https://openalex.org/W3012366959","https://openalex.org/W3216772467","https://openalex.org/W4206822501","https://openalex.org/W4214717370","https://openalex.org/W4252532437","https://openalex.org/W4285175581","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894","https://openalex.org/W4318603635"],"abstract_inverted_index":{"In":[0,103,180],"the":[1,5,31,51,62,71,93,99,173,195,202,208],"last":[2],"few":[3],"years,":[4],"deep":[6,39],"learning":[7,16,40,43,185,190],"paradigm":[8],"has":[9,33],"experienced":[10],"huge":[11],"success":[12],"in":[13,50,177,200],"various":[14],"machine":[15],"research":[17],"areas":[18,52],"like":[19,53],"computer":[20],"vision,":[21],"drug":[22],"discoveries,":[23],"natural":[24],"language":[25],"processing,":[26],"and":[27,58,117,145,152,157,188],"combinatorial":[28],"optimizations.":[29],"Moreover,":[30],"world":[32],"witnessed":[34],"remarkable":[35],"achievements":[36],"when":[37],"combining":[38],"with":[41,113],"reinforcement":[42,184],"(now":[44],"known":[45,141],"as":[46,142,165,168],"Deep":[47,66,137,143],"Reinforcement":[48,67],"Learning)":[49],"robotics,":[54],"video":[55],"games,":[56],"business,":[57],"healthcare.":[59],"One":[60],"of":[61,65,172],"strongest":[63],"parts":[64],"Learning":[68],"(DRL)":[69],"is":[70,82,111,121,163,170,211],"ability":[72],"to":[73,91,97,182],"solve":[74],"sequential":[75],"decision-making":[76],"problems.":[77],"The":[78,119,150,159],"inventory":[79,101],"control":[80],"problem":[81,120],"one":[83,171],"such":[84],"field":[85],"where":[86],"DRL":[87],"can":[88],"be":[89],"applied":[90],"learn":[92],"optimal":[94,203],"ordering":[95,204],"policy":[96,162],"minimize":[98],"total":[100,209],"cost.":[102],"this":[104],"paper,":[105],"a":[106,166],"linear":[107],"supply":[108],"chain":[109],"model":[110,197],"considered":[112],"stochastic":[114],"lead":[115],"time":[116],"demand.":[118],"then":[122,130],"modeled":[123],"into":[124],"Markov":[125],"Decision":[126],"Processes":[127],"(MDP).":[128],"We":[129],"designed":[131],"three":[132],"different":[133],"agents:":[134],"Q-learning":[135,151],"agent,":[136],"Q-network":[138],"(DQN,":[139],"also":[140],"Q-Learning),":[144],"(R,":[146,160,192],"S)":[147,161,193],"policy-based":[148],"agent.":[149],"DQN":[153,196],"agents":[154],"were":[155],"trained":[156],"evaluated.":[158],"used":[164],"baseline":[167],"it":[169],"most":[174],"popular":[175],"policies":[176],"business":[178],"organizations.":[179],"comparison":[181],"traditional":[183],"(i.e":[186],"Q-learning)":[187],"rule-based":[189],"(i.e.":[191],"policy),":[194],"performs":[198],"better":[199],"making":[201],"decision":[205],"so":[206],"that":[207],"cost":[210],"minimized.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}