{"id":"https://openalex.org/W3092224582","doi":"https://doi.org/10.1109/case48305.2020.9216863","title":"Deep Q-learning for the Control of PLC-based Automated Production Systems","display_name":"Deep Q-learning for the Control of PLC-based Automated Production Systems","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3092224582","doi":"https://doi.org/10.1109/case48305.2020.9216863","mag":"3092224582"},"language":"en","primary_location":{"id":"doi:10.1109/case48305.2020.9216863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9216863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","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/A5022995247","display_name":"Jonas Zinn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonas Zinn","raw_affiliation_strings":["Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071323487","display_name":"Birgit Vogel\u2010Heuser","orcid":"https://orcid.org/0000-0003-2785-8819"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birgit Vogel-Heuser","raw_affiliation_strings":["Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010775928","display_name":"Paulina Ockier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paulina Ockier","raw_affiliation_strings":["Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022995247"],"corresponding_institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.7356,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71360635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1434","last_page":"1440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.991100013256073,"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/T14011","display_name":"Elevator Systems and Control","score":0.991100013256073,"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":0.988099992275238,"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":0.9664999842643738,"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/computer-science","display_name":"Computer science","score":0.6900629997253418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6772293448448181},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.6747794151306152},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6490378975868225},{"id":"https://openalex.org/keywords/programmable-logic-controller","display_name":"Programmable logic controller","score":0.6249632239341736},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5355532169342041},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5190104246139526},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5119417905807495},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5002603530883789},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47299107909202576},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4349883794784546},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.419466108083725},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.41095343232154846},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3782946765422821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3459670841693878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27007901668548584},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19651448726654053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900629997253418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6772293448448181},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.6747794151306152},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6490378975868225},{"id":"https://openalex.org/C37374048","wikidata":"https://www.wikidata.org/wiki/Q188674","display_name":"Programmable logic controller","level":2,"score":0.6249632239341736},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5355532169342041},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5190104246139526},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5119417905807495},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5002603530883789},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47299107909202576},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4349883794784546},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.419466108083725},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.41095343232154846},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3782946765422821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3459670841693878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27007901668548584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19651448726654053},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/case48305.2020.9216863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9216863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1579112","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1579112","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2416041116","https://openalex.org/W2528489519","https://openalex.org/W2575705757","https://openalex.org/W2604216058","https://openalex.org/W2746553466","https://openalex.org/W2749779701","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2785342287","https://openalex.org/W2921790298","https://openalex.org/W2944559718","https://openalex.org/W2951799221","https://openalex.org/W2963477884","https://openalex.org/W2963544079","https://openalex.org/W2964001908","https://openalex.org/W2964121744","https://openalex.org/W2964291307","https://openalex.org/W2982316857","https://openalex.org/W3103780890","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6740801417","https://openalex.org/W6744339171","https://openalex.org/W6748566876"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W4243995220","https://openalex.org/W2095055219","https://openalex.org/W2482527088","https://openalex.org/W2362374543","https://openalex.org/W2116295091","https://openalex.org/W4319430205","https://openalex.org/W3121711078","https://openalex.org/W2085265870","https://openalex.org/W2348196682"],"abstract_inverted_index":{"This":[0],"paper":[1],"evaluates":[2],"the":[3,34,45,109,118,124,154],"use":[4,70],"of":[5,37,39,47,81,111,127],"Deep":[6,63,128],"Reinforcement":[7],"Learning":[8],"to":[9,33,58,67,92,117,132,145,163,166],"control":[10],"Programmable":[11],"Logic":[12],"Controller-based":[13],"automated":[14],"Production":[15],"Systems,":[16],"which":[17,40],"are":[18,24,56,115],"characterized":[19],"by":[20,76],"multiple":[21],"end-effectors":[22],"that":[23],"actuated":[25],"in":[26,78],"only":[27,41],"one":[28],"or":[29],"two":[30],"axes.":[31],"Due":[32],"large":[35],"number":[36],"actuators":[38],"a":[42,48,51,68,79,83],"few":[43],"affect":[44],"processing":[46],"workpiece":[49,138,170],"at":[50],"given":[52],"time,":[53],"these":[54],"systems":[55],"challenging":[57],"learn.":[59],"In":[60,152],"this":[61,112],"paper,":[62,113],"Q-learning":[64,129],"is":[65,89,130,161],"applied":[66,116],"small":[69],"case":[71],"focusing":[72],"on":[73],"sorting":[74],"workpieces":[75],"color":[77],"simulation":[80],"such":[82],"production":[84],"system.":[85],"The":[86],"basic":[87],"algorithm":[88,155],"hereby":[90],"compared":[91],"four":[93,158],"commonly":[94],"used":[95],"extensions:":[96],"Double":[97],"Q-learning,":[98],"Dueling":[99],"Networks,":[100],"Prioritized":[101],"Experience":[102,106],"Replay,":[103],"and":[104,120],"Hindsight":[105],"Replay.":[107],"For":[108],"scope":[110],"simplifications":[114],"state":[119],"action":[121],"space.":[122],"While":[123],"baseline":[125],"implementation":[126],"able":[131,162],"correctly":[133],"sort":[134],"30":[135],"previously":[136],"seen":[137],"combinations,":[139],"it":[140],"does":[141],"not":[142],"reliably":[143,164],"generalize":[144,165],"unseen":[146],"ones":[147],"within":[148],"45,000":[149],"training":[150],"episodes.":[151],"contrast,":[153],"using":[156],"all":[157,167],"considered":[159],"extensions":[160],"81":[168],"possible":[169],"combinations.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}