{"id":"https://openalex.org/W2163285971","doi":"https://doi.org/10.1109/icsmc.2007.4414132","title":"Q-learning in a competitive supply chain","display_name":"Q-learning in a competitive supply chain","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2163285971","doi":"https://doi.org/10.1109/icsmc.2007.4414132","mag":"2163285971"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2007.4414132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4414132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","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/A5098636394","display_name":"Tim van Tongeren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim van Tongeren","raw_affiliation_strings":["Type2 Solutions, Ridderkerk, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Type2 Solutions, Ridderkerk, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080242338","display_name":"Uzay Kaymak","orcid":"https://orcid.org/0000-0002-4500-9098"},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Uzay Kaymak","raw_affiliation_strings":["Econometric Institute Erasmus University Rotterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Econometric Institute Erasmus University Rotterdam, Netherlands","institution_ids":["https://openalex.org/I913958620"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011873850","display_name":"David Naso","orcid":"https://orcid.org/0000-0002-7948-8226"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"David Naso","raw_affiliation_strings":["Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041336477","display_name":"Eelco van Asperen","orcid":null},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Eelco van Asperen","raw_affiliation_strings":["Econometric Institute Erasmus University Rotterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Econometric Institute Erasmus University Rotterdam, Netherlands","institution_ids":["https://openalex.org/I913958620"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9285,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.80513484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1211","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9958999752998352,"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":0.9958999752998352,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9728000164031982,"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/supply-chain","display_name":"Supply chain","score":0.8990144729614258},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7976059317588806},{"id":"https://openalex.org/keywords/profitability-index","display_name":"Profitability index","score":0.7787595987319946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57358717918396},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.4214574098587036},{"id":"https://openalex.org/keywords/supply-chain-management","display_name":"Supply chain management","score":0.4177604019641876},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.35432004928588867},{"id":"https://openalex.org/keywords/industrial-organization","display_name":"Industrial organization","score":0.335456520318985},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3256238102912903},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.31682509183883667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22489586472511292},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.17647194862365723},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1626257300376892}],"concepts":[{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.8990144729614258},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7976059317588806},{"id":"https://openalex.org/C129361004","wikidata":"https://www.wikidata.org/wiki/Q2470236","display_name":"Profitability index","level":2,"score":0.7787595987319946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57358717918396},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.4214574098587036},{"id":"https://openalex.org/C44104985","wikidata":"https://www.wikidata.org/wiki/Q492886","display_name":"Supply chain management","level":3,"score":0.4177604019641876},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.35432004928588867},{"id":"https://openalex.org/C40700","wikidata":"https://www.wikidata.org/wiki/Q1411783","display_name":"Industrial organization","level":1,"score":0.335456520318985},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3256238102912903},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.31682509183883667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22489586472511292},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.17647194862365723},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1626257300376892},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icsmc.2007.4414132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4414132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/44e11309-9e8d-4e2c-b65a-9d9afa6504e3","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/44e11309-9e8d-4e2c-b65a-9d9afa6504e3","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tongeren, van, T, Kaymak, U, Naso, D & Asperen, van, E 2007, Q-learning in a competitive supply chain. in IEEE International Conference on Systems, Man and Cybernetics (ISIC), 7-10 October 2007, Montreal. Institute of Electrical and Electronics Engineers, Piscataway, pp. 1211-1216. https://doi.org/10.1109/ICSMC.2007.4414132","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/44e11309-9e8d-4e2c-b65a-9d9afa6504e3","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/44e11309-9e8d-4e2c-b65a-9d9afa6504e3","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":"IEEE International Conference on Systems, Man and Cybernetics (ISIC), 7-10 October 2007, Montreal, 1211 - 1216","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1991642024","https://openalex.org/W2026387568","https://openalex.org/W2053616263","https://openalex.org/W2104665511","https://openalex.org/W2104925392","https://openalex.org/W2105454737","https://openalex.org/W2107726111","https://openalex.org/W2119491217","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2153159747","https://openalex.org/W2158330236","https://openalex.org/W2164637474","https://openalex.org/W2491811284","https://openalex.org/W2610191465","https://openalex.org/W3167111994","https://openalex.org/W4214717370","https://openalex.org/W4238713889","https://openalex.org/W4252999557","https://openalex.org/W4255047891","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W3125099825","https://openalex.org/W25115902","https://openalex.org/W2753408573","https://openalex.org/W4285147705","https://openalex.org/W1986338457","https://openalex.org/W2066844180","https://openalex.org/W2983500849","https://openalex.org/W3024999678","https://openalex.org/W388184414"],"abstract_inverted_index":{"The":[0],"participants":[1],"in":[2,11,77,96],"a":[3,12,47,78,104],"competitive":[4],"supply":[5,36,58,80,93],"chain":[6,37,59,81],"take":[7],"their":[8,27],"decisions":[9,52],"individually":[10],"distributed":[13],"environment":[14],"and":[15,50,82],"independent":[16],"of":[17,34,56],"one":[18,49],"another.":[19],"At":[20],"the":[21,31,35,51,57,92,97,110,127],"same":[22],"time,":[23],"they":[24,87,121],"must":[25],"coordinate":[26],"actions":[28],"so":[29],"that":[30,109],"total":[32],"profitability":[33],"is":[38,43,101,107],"safeguarded.":[39],"This":[40],"decision":[41],"problem":[42],"known":[44],"to":[45,62,90,126],"be":[46],"difficult":[48],"at":[53],"different":[54],"stages":[55],"may":[60],"lead":[61],"large":[63],"oscillations":[64],"if":[65],"not":[66,123],"coordinated":[67],"properly.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"consider":[73],"reinforcement":[74,111],"learning":[75,112],"agents":[76,113],"multi-echelon":[79],"study":[83],"under":[84],"which":[85],"conditions":[86],"are":[88],"able":[89],"manage":[91],"chain.":[94],"Q-learning":[95],"well-known":[98],"beer":[99],"game":[100],"used":[102],"as":[103],"case.":[105],"It":[106],"found":[108],"can":[114],"learn":[115],"better":[116],"policies":[117],"than":[118],"humans,":[119],"although":[120],"do":[122],"always":[124],"converge":[125],"optimal":[128],"policy.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}