{"id":"https://openalex.org/W3092194255","doi":"https://doi.org/10.15439/2020f100","title":"Reinforcement Learning Algorithms for Online Single-Machine Scheduling","display_name":"Reinforcement Learning Algorithms for Online Single-Machine Scheduling","publication_year":2020,"publication_date":"2020-09-26","ids":{"openalex":"https://openalex.org/W3092194255","doi":"https://doi.org/10.15439/2020f100","mag":"3092194255"},"language":"en","primary_location":{"id":"doi:10.15439/2020f100","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f100","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/100.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2020/drp/pdf/100.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100713782","display_name":"Yuanyuan Li","orcid":"https://orcid.org/0000-0001-6721-9128"},"institutions":[{"id":"https://openalex.org/I4210155299","display_name":"LINKS Foundation","ror":"https://ror.org/059r3nh67","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155299"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Yuanyuan Li","raw_affiliation_strings":["LINKS Foundation -Advanced Computing and Applications, 10138 Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINKS Foundation -Advanced Computing and Applications, 10138 Torino, Italy","institution_ids":["https://openalex.org/I4210155299"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026981405","display_name":"Edoardo Fadda","orcid":"https://orcid.org/0000-0002-5599-6349"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Edoardo Fadda","raw_affiliation_strings":["Department of Control and Computer Engineering, Politecnico di Torino, 10129 Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Politecnico di Torino, 10129 Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072270457","display_name":"Daniele Manerba","orcid":"https://orcid.org/0000-0002-3502-5289"},"institutions":[{"id":"https://openalex.org/I79940851","display_name":"University of Brescia","ror":"https://ror.org/02q2d2610","country_code":"IT","type":"education","lineage":["https://openalex.org/I79940851"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Manerba","raw_affiliation_strings":["Department of Information Engineering, University of Brescia, 25123 Brescia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Brescia, 25123 Brescia, Italy","institution_ids":["https://openalex.org/I79940851"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064842708","display_name":"Roberto Tadei","orcid":"https://orcid.org/0000-0003-0828-424X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Tadei","raw_affiliation_strings":["Department of Control and Computer Engineering, Politecnico di Torino, 10129 Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Politecnico di Torino, 10129 Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090105160","display_name":"Olivier Terzo","orcid":"https://orcid.org/0000-0001-8482-2607"},"institutions":[{"id":"https://openalex.org/I4210155299","display_name":"LINKS Foundation","ror":"https://ror.org/059r3nh67","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155299"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Olivier Terzo","raw_affiliation_strings":["LINKS Foundation -Advanced Computing and Applications, 10138 Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINKS Foundation -Advanced Computing and Applications, 10138 Torino, Italy","institution_ids":["https://openalex.org/I4210155299"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100713782"],"corresponding_institution_ids":["https://openalex.org/I4210155299"],"apc_list":null,"apc_paid":null,"fwci":7.0216,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.98107958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"21","issue":null,"first_page":"277","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9995999932289124,"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/T12288","display_name":"Optimization and Search Problems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8303506374359131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7645978927612305},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6429907083511353},{"id":"https://openalex.org/keywords/tardiness","display_name":"Tardiness","score":0.579316258430481},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4925466477870941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4782090187072754},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4676840901374817},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4242698848247528},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4139256775379181},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28515344858169556},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.1250251829624176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10620436072349548}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8303506374359131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645978927612305},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6429907083511353},{"id":"https://openalex.org/C2778047078","wikidata":"https://www.wikidata.org/wiki/Q82299449","display_name":"Tardiness","level":4,"score":0.579316258430481},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4925466477870941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4782090187072754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4676840901374817},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4242698848247528},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4139256775379181},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28515344858169556},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.1250251829624176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10620436072349548},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2020f100","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f100","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/100.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:b8408ed442c045fea7fa46ae778db3f7","is_oa":false,"landing_page_url":"https://doaj.org/article/b8408ed442c045fea7fa46ae778db3f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Annals of computer science and information systems, Vol 21, Pp 277-283 (2020)","raw_type":"article"},{"id":"pmh:oai:iris.unibs.it:11379/534367","is_oa":true,"landing_page_url":"https://annals-csis.org/Volume_21/drp/100.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400804","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Brescia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.15439/2020f100","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2020f100","pdf_url":"https://annals-csis.org/proceedings/2020/drp/pdf/100.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G1464101492","display_name":null,"funder_award_id":"FESR 2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G501661366","display_name":null,"funder_award_id":"POR FESR 2014-2020","funder_id":"https://openalex.org/F4320326081","funder_display_name":"Regione Piemonte"},{"id":"https://openalex.org/G5634946813","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6741047363","display_name":null,"funder_award_id":"Contract No. 319-31","funder_id":"https://openalex.org/F4320326081","funder_display_name":"Regione Piemonte"},{"id":"https://openalex.org/G72824567","display_name":null,"funder_award_id":"POR FESR 2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320326081","display_name":"Regione Piemonte","ror":null},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092194255.pdf","grobid_xml":"https://content.openalex.org/works/W3092194255.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1228503213","https://openalex.org/W1501070407","https://openalex.org/W1547180210","https://openalex.org/W1757796397","https://openalex.org/W2014034914","https://openalex.org/W2061672548","https://openalex.org/W2089269509","https://openalex.org/W2100131857","https://openalex.org/W2121863487","https://openalex.org/W2148301389","https://openalex.org/W2150339816","https://openalex.org/W2171834356","https://openalex.org/W2187600643","https://openalex.org/W2194966727","https://openalex.org/W2315340820","https://openalex.org/W2472472094","https://openalex.org/W2597517657","https://openalex.org/W2735963166","https://openalex.org/W2783011664","https://openalex.org/W2917022701","https://openalex.org/W2970515370","https://openalex.org/W2973250052","https://openalex.org/W3011120880","https://openalex.org/W3013294044","https://openalex.org/W3083951899","https://openalex.org/W3114375073","https://openalex.org/W4236962151","https://openalex.org/W4239337465","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6673012173","https://openalex.org/W6675087593"],"related_works":["https://openalex.org/W3097192092","https://openalex.org/W3029619930","https://openalex.org/W2061005265","https://openalex.org/W3008231844","https://openalex.org/W2358315670","https://openalex.org/W3204654320","https://openalex.org/W2768876727","https://openalex.org/W2128410848","https://openalex.org/W2102390841","https://openalex.org/W2118368532"],"abstract_inverted_index":{"Online":[0],"scheduling":[1,29,60,90],"has":[2],"been":[3],"an":[4,34],"attractive":[5],"field":[6],"of":[7,43,88],"research":[8],"for":[9],"over":[10],"three":[11],"decades.":[12],"Some":[13],"recent":[14],"developments":[15],"suggest":[16],"that":[17,78],"Reinforcement":[18],"Learning":[19],"(RL)":[20],"techniques":[21,72],"have":[22],"the":[23,44,57,85,89],"potential":[24],"to":[25,56,66],"deal":[26],"with":[27],"online":[28,58],"issues":[30],"effectively.":[31],"Driven":[32],"by":[33],"industrial":[35],"application,":[36],"in":[37,83],"this":[38],"paper":[39],"we":[40],"apply":[41],"four":[42],"most":[45],"important":[46],"RL":[47],"techniques,":[48],"namely":[49],"Q-learning,":[50],"Sarsa,":[51],"Watkins's":[52,79],"Q(),":[53],"and":[54],"Sarsa(),":[55],"single-machine":[59],"problem.":[61],"Our":[62],"main":[63],"goal":[64],"is":[65],"provide":[67],"insights":[68],"on":[69],"how":[70],"such":[71],"perform.":[73],"The":[74],"numerical":[75],"results":[76],"show":[77],"Q()":[80],"performs":[81],"best":[82],"minimizing":[84],"total":[86],"tardiness":[87],"process.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}