{"id":"https://openalex.org/W4205805428","doi":"https://doi.org/10.1109/ieem50564.2021.9673034","title":"Control of Shared Production Buffers: A Reinforcement Learning Approach","display_name":"Control of Shared Production Buffers: A Reinforcement Learning Approach","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4205805428","doi":"https://doi.org/10.1109/ieem50564.2021.9673034"},"language":"en","primary_location":{"id":"doi:10.1109/ieem50564.2021.9673034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieem50564.2021.9673034","pdf_url":null,"source":{"id":"https://openalex.org/S4363607822","display_name":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","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":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5039939751","display_name":"N. Krippendorff","orcid":null},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"N. Krippendorff","raw_affiliation_strings":["Institute of Management and Economics, Clausthal University for Technology, Clausthal-Zellerfeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Management and Economics, Clausthal University for Technology, Clausthal-Zellerfeld, Germany","institution_ids":["https://openalex.org/I43980791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073283046","display_name":"Christoph Schwindt","orcid":null},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"C. Schwindt","raw_affiliation_strings":["Institute of Management and Economics, Clausthal University for Technology, Clausthal-Zellerfeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Management and Economics, Clausthal University for Technology, Clausthal-Zellerfeld, Germany","institution_ids":["https://openalex.org/I43980791"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43980791"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28008204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"703","last_page":"707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.9983000159263611,"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/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.9983000159263611,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9944999814033508,"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"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9800999760627747,"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":0.8500160574913025},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8413448333740234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557042241096497},{"id":"https://openalex.org/keywords/uniformization","display_name":"Uniformization (probability theory)","score":0.6900330781936646},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5953898429870605},{"id":"https://openalex.org/keywords/production-control","display_name":"Production control","score":0.5898165106773376},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5870757102966309},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5410223603248596},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5386054515838623},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4966786503791809},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4699583053588867},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.4342181086540222},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4271089732646942},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2787249684333801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24597913026809692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2096962332725525},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18964064121246338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15616270899772644},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.14790508151054382}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8500160574913025},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8413448333740234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557042241096497},{"id":"https://openalex.org/C149260544","wikidata":"https://www.wikidata.org/wiki/Q7885142","display_name":"Uniformization (probability theory)","level":5,"score":0.6900330781936646},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5953898429870605},{"id":"https://openalex.org/C2780682718","wikidata":"https://www.wikidata.org/wiki/Q16321575","display_name":"Production control","level":3,"score":0.5898165106773376},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5870757102966309},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5410223603248596},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5386054515838623},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4966786503791809},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4699583053588867},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.4342181086540222},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4271089732646942},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2787249684333801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24597913026809692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2096962332725525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18964064121246338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15616270899772644},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.14790508151054382},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":1,"locations":[{"id":"doi:10.1109/ieem50564.2021.9673034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieem50564.2021.9673034","pdf_url":null,"source":{"id":"https://openalex.org/S4363607822","display_name":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","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":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1971168250","https://openalex.org/W2043806986","https://openalex.org/W2054745319","https://openalex.org/W2419593711","https://openalex.org/W2487144912","https://openalex.org/W2594222130","https://openalex.org/W2623569188","https://openalex.org/W2761345667","https://openalex.org/W2792256081","https://openalex.org/W4213251304","https://openalex.org/W4241616730","https://openalex.org/W6734359640"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W2516770623","https://openalex.org/W4205805428"],"abstract_inverted_index":{"We":[0,43,126],"consider":[1],"a":[2,45,52,66,86,92,95,107,128,146,150],"buffer":[3,58,68],"control":[4,16],"problem":[5,50,70,99,115],"arising":[6],"in":[7,118,145],"stochastic":[8],"flow":[9,80],"lines":[10],"with":[11,55,149],"shared":[12],"production":[13,41,88],"buffers.":[14],"Buffer":[15],"relies":[17],"on":[18,38],"decision":[19,98,114],"rules":[20],"which":[21],"determine":[22],"transfers":[23],"of":[24,36,48,132],"items":[25],"between":[26],"buffers":[27],"and":[28,59,65,120,141],"machines":[29],"at":[30],"the":[31,39,49,79,112,143],"release":[32],"or":[33],"completion":[34],"times":[35],"parts":[37],"different":[40],"stages.":[42],"devise":[44],"conceptual":[46],"model":[47],"for":[51],"basic":[53],"scenario":[54],"one":[56],"central":[57],"explain":[60],"how":[61],"general":[62],"system":[63],"configurations":[64],"tactical":[67],"allocation":[69],"can":[71,82],"be":[72,83],"modeled":[73],"within":[74],"this":[75],"framework.":[76],"Assuming":[77],"that":[78],"line":[81],"represented":[84],"as":[85,94],"Markovian":[87],"system,":[89],"we":[90],"provide":[91],"formulation":[93],"continuous-time":[96],"Markov":[97,113],"admitting":[100],"an":[101,137],"optimal":[102,138],"stationary":[103,139],"policy.":[104],"By":[105],"applying":[106],"uniformization":[108],"approach":[109,144],"from":[110],"literature,":[111],"is":[116],"discretized":[117],"time":[119],"thus":[121],"amenable":[122],"to":[123,136],"standard":[124],"algorithms.":[125],"propose":[127],"simple":[129],"Q-learning":[130],"implementation":[131],"reinforcement":[133],"learning":[134],"converging":[135],"policy":[140],"validate":[142],"numerical":[147],"experiment":[148],"small":[151],"toy":[152],"problem.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}