{"id":"https://openalex.org/W4391020227","doi":"https://doi.org/10.1109/cdc49753.2023.10383904","title":"Multi-Agent Reinforcement Learning for Resource Allocation in Large-Scale Robotic Warehouse Sortation Centers","display_name":"Multi-Agent Reinforcement Learning for Resource Allocation in Large-Scale Robotic Warehouse Sortation Centers","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020227","doi":"https://doi.org/10.1109/cdc49753.2023.10383904"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","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/A5009683062","display_name":"Yi Shen","orcid":"https://orcid.org/0009-0009-1578-4542"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Shen","raw_affiliation_strings":["Duke University,Department of Mechanical Engineering and Materials Science","Department of Mechanical Engineering and Materials Science, Duke University","Amazon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Department of Mechanical Engineering and Materials Science","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Mechanical Engineering and Materials Science, Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Amazon Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017824599","display_name":"Benjamin McClosky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin McClosky","raw_affiliation_strings":["Amazon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085289306","display_name":"Joseph W. Durham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph W. Durham","raw_affiliation_strings":["Amazon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University,Department of Mechanical Engineering and Materials Science","Department of Mechanical Engineering and Materials Science, Duke University","Amazon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Department of Mechanical Engineering and Materials Science","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Mechanical Engineering and Materials Science, Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Amazon Robotics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009683062"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.1561,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82518841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7137","last_page":"7143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9972000122070312,"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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9972000122070312,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9926000237464905,"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/T12782","display_name":"Assembly Line Balancing Optimization","score":0.9883999824523926,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8563252687454224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433250546455383},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.6336759328842163},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5852060317993164},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5050743222236633},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4900323152542114},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4764176607131958},{"id":"https://openalex.org/keywords/destinations","display_name":"Destinations","score":0.4666241407394409},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44667619466781616},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44646409153938293},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4194394052028656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3669602870941162},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33295440673828125},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17055293917655945},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10075947642326355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09039250016212463}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8563252687454224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433250546455383},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6336759328842163},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5852060317993164},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5050743222236633},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4900323152542114},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4764176607131958},{"id":"https://openalex.org/C2776687071","wikidata":"https://www.wikidata.org/wiki/Q5265193","display_name":"Destinations","level":3,"score":0.4666241407394409},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44667619466781616},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44646409153938293},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4194394052028656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3669602870941162},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33295440673828125},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17055293917655945},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10075947642326355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09039250016212463},{"id":"https://openalex.org/C18918823","wikidata":"https://www.wikidata.org/wiki/Q49389","display_name":"Tourism","level":2,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.550000011920929,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1119549075","https://openalex.org/W1549280300","https://openalex.org/W1641379095","https://openalex.org/W1983317903","https://openalex.org/W2007990112","https://openalex.org/W2083276257","https://openalex.org/W2145339207","https://openalex.org/W2161129362","https://openalex.org/W2391684340","https://openalex.org/W2468807217","https://openalex.org/W2626637010","https://openalex.org/W2905057216","https://openalex.org/W2949794851","https://openalex.org/W2952367389","https://openalex.org/W3130896630","https://openalex.org/W3198784911","https://openalex.org/W4285735429","https://openalex.org/W4288594419","https://openalex.org/W6632662516","https://openalex.org/W6637561705","https://openalex.org/W6684185872"],"related_works":["https://openalex.org/W2361805396","https://openalex.org/W2972254340","https://openalex.org/W1805912688","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W2373973507","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Robotic":[0],"sortation":[1,29,110,138],"centers":[2],"use":[3],"mobile":[4],"robots":[5],"to":[6,41,105],"sort":[7],"packages":[8,22,90],"by":[9,27],"their":[10],"destinations.":[11],"The":[12],"destination-to-sort-location":[13],"(chute)":[14],"mapping":[15,45,122],"can":[16,24,118],"significantly":[17],"impact":[18],"the":[19,28,55,59,64,69,77,86,95,100,109],"volume":[20],"of":[21,49,58,71,102],"that":[23,114,130],"be":[25],"sorted":[26],"floor.":[30,111],"In":[31],"this":[32],"work,":[33],"we":[34,62,93],"propose":[35],"a":[36],"multi-agent":[37],"reinforcement":[38],"learning":[39],"method":[40],"solve":[42,119],"large-scale":[43],"chute":[44,121],"problems":[46,123],"with":[47,76],"hundreds":[48],"agents":[50],"(the":[51],"destinations).":[52],"To":[53,80],"address":[54],"exponential":[56],"growth":[57],"state-action":[60],"space,":[61],"decompose":[63],"joint":[65],"action-value":[66,73,97],"function":[67],"as":[68],"sum":[70],"local":[72,96],"functions":[74,98],"associated":[75],"individual":[78],"agents.":[79],"incorporate":[81],"robot":[82],"congestion":[83],"effects":[84],"on":[85,108],"rates":[87],"at":[88],"which":[89],"are":[91,131],"sorted,":[92],"couple":[94],"through":[99],"states":[101],"destinations":[103],"mapped":[104],"nearby":[106],"chutes":[107],"We":[112],"show":[113],"our":[115],"proposed":[116],"framework":[117],"large":[120],"and":[124],"outperforms":[125],"static":[126],"or":[127],"reactive":[128],"policies":[129],"commonly":[132],"used":[133],"in":[134,136],"practice":[135],"robotic":[137],"facilities.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2025-10-10T00:00:00"}