{"id":"https://openalex.org/W7166694427","doi":"https://doi.org/10.7148/2026-0063","title":"Towards efficient and sustainable operations in supply chain management: a reinforcement learning approach","display_name":"Towards efficient and sustainable operations in supply chain management: a reinforcement learning approach","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7166694427","doi":"https://doi.org/10.7148/2026-0063"},"language":null,"primary_location":{"id":"doi:10.7148/2026-0063","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0063","pdf_url":"https://doi.org/10.7148/2026-0063","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7148/2026-0063","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139657357","display_name":"Djonathan Quadras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Djonathan Quadras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047834203","display_name":"Romeo Bandinelli","orcid":"https://orcid.org/0000-0002-5547-4225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romeo Bandinelli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084924575","display_name":"Virginia Fani","orcid":"https://orcid.org/0000-0003-3668-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Virginia Fani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5238999724388123,"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":0.5238999724388123,"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/T10539","display_name":"Sustainable Supply Chain Management","score":0.14169999957084656,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"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/T11864","display_name":"Supply Chain Resilience and Risk Management","score":0.09749999642372131,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"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/supply-chain","display_name":"Supply chain","score":0.6766999959945679},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6152999997138977},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/sustainability","display_name":"Sustainability","score":0.47530001401901245},{"id":"https://openalex.org/keywords/supply-chain-optimization","display_name":"Supply chain optimization","score":0.46970000863075256},{"id":"https://openalex.org/keywords/supply-chain-management","display_name":"Supply chain management","score":0.4262999892234802},{"id":"https://openalex.org/keywords/service-management","display_name":"Service management","score":0.40389999747276306},{"id":"https://openalex.org/keywords/service-level","display_name":"Service level","score":0.374099999666214},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3727000057697296}],"concepts":[{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.6766999959945679},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5297999978065491},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C66204764","wikidata":"https://www.wikidata.org/wiki/Q219416","display_name":"Sustainability","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C2779150434","wikidata":"https://www.wikidata.org/wiki/Q7644532","display_name":"Supply chain optimization","level":4,"score":0.46970000863075256},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C44104985","wikidata":"https://www.wikidata.org/wiki/Q492886","display_name":"Supply chain management","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C48840187","wikidata":"https://www.wikidata.org/wiki/Q689042","display_name":"Service management","level":4,"score":0.40389999747276306},{"id":"https://openalex.org/C181889124","wikidata":"https://www.wikidata.org/wiki/Q380204","display_name":"Service level","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C192639820","wikidata":"https://www.wikidata.org/wiki/Q1114469","display_name":"Supply chain risk management","level":5,"score":0.3456000089645386},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C182299520","wikidata":"https://www.wikidata.org/wiki/Q1289588","display_name":"Total cost","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2778976125","wikidata":"https://www.wikidata.org/wiki/Q288401","display_name":"Carbon tax","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C10431821","wikidata":"https://www.wikidata.org/wiki/Q6510174","display_name":"Learning effect","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C120330832","wikidata":"https://www.wikidata.org/wiki/Q166656","display_name":"Supply and demand","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C179366874","wikidata":"https://www.wikidata.org/wiki/Q1185130","display_name":"Demand management","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.27090001106262207},{"id":"https://openalex.org/C2986883954","wikidata":"https://www.wikidata.org/wiki/Q1362005","display_name":"Operational costs","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2026-0063","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0063","pdf_url":"https://doi.org/10.7148/2026-0063","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2026-0063","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0063","pdf_url":"https://doi.org/10.7148/2026-0063","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4777594804763794,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166694427.pdf","grobid_xml":"https://content.openalex.org/works/W7166694427.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"supply":[1,79],"chain":[2],"management":[3],"requires":[4],"balancing":[5],"economic":[6],"performance,":[7],"operational":[8,146],"efficiency,":[9],"and":[10,56,64,87,100,105,122,142],"environmental":[11],"sustainability":[12],"among":[13],"dynamic":[14],"demand":[15],"uncertainties.":[16],"Traditional":[17],"analytical":[18],"models":[19],"often":[20],"fail":[21],"to":[22,47,74,132],"capture":[23],"the":[24,33,42,49,154,172,175],"stochastic":[25,92],"nature":[26],"of":[27,44,156],"these":[28],"complex,":[29],"multi-echelon":[30],"networks,":[31],"driving":[32],"need":[34],"for":[35],"advanced":[36],"data-driven":[37],"methodologies.":[38],"This":[39],"study":[40],"investigates":[41],"application":[43],"Reinforcement":[45],"Learning":[46],"address":[48],"gap":[50],"in":[51,119],"jointly":[52],"optimizing":[53],"procurement,":[54],"production,":[55],"replenishment":[57],"decisions":[58],"while":[59,164],"explicitly":[60],"minimizing":[61],"carbon":[62,181],"emissions":[63],"maintaining":[65],"high":[66],"service":[67],"levels.":[68,170],"A":[69],"simulation-based":[70],"approach":[71],"was":[72],"developed":[73],"model":[75],"a":[76,116,133,159],"three-echelon":[77],"juice":[78],"chain,":[80],"comprising":[81],"two":[82],"suppliers,":[83],"one":[84],"manufacturing":[85],"factory,":[86],"five":[88],"regional":[89],"warehouses":[90],"facing":[91],"seasonal":[93],"demand.":[94],"Two":[95],"algorithms,":[96],"Proximal":[97,125],"Policy":[98,126],"Optimization":[99,127],"Advantage":[101,176],"Actor-Critic,":[102],"were":[103],"trained":[104],"evaluated":[106],"within":[107],"this":[108],"continuous,":[109],"multi-objective":[110],"environment.":[111],"The":[112,124],"computational":[113],"results":[114],"reveal":[115],"significant":[117],"divergence":[118],"policy":[120],"stability":[121],"performance.":[123],"algorithm":[128],"demonstrated":[129],"superiority,":[130],"converging":[131],"low-variance":[134],"strategy":[135],"that":[136],"generated":[137],"approximately":[138],"35%":[139],"more":[140],"profit":[141],"reduced":[143],"total":[144],"accumulated":[145],"costs":[147],"by":[148],"33%.":[149],"Furthermore,":[150],"it":[151],"successfully":[152],"optimized":[153],"distribution":[155],"goods,":[157],"achieving":[158],"superior":[160],"customer":[161],"fulfilment":[162],"rate":[163],"simultaneously":[165],"operating":[166],"with":[167],"lower":[168,180],"inventory":[169],"On":[171],"other":[173],"hand,":[174],"Actor-Critic":[177],"agent":[178],"achieved":[179],"emissions.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-01T00:00:00"}