{"id":"https://openalex.org/W4411232012","doi":"https://doi.org/10.1109/lra.2025.3579647","title":"Reinforcement Learning for Multi-Agent Path Finding in Large-Scale Warehouses via Distributed Policy Evolution","display_name":"Reinforcement Learning for Multi-Agent Path Finding in Large-Scale Warehouses via Distributed Policy Evolution","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W4411232012","doi":"https://doi.org/10.1109/lra.2025.3579647"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3579647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3579647","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5031948999","display_name":"Qinru Shi","orcid":"https://orcid.org/0000-0003-0671-2423"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinru Shi","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033808402","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0003-0693-6574"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-0693-6574","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003643230","display_name":"Senlin Zhang","orcid":"https://orcid.org/0000-0001-5117-3110"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senlin Zhang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-3110","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3422-944X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031948999"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":3.3997,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92556258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"10","issue":"8","first_page":"7843","last_page":"7850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.995199978351593,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.8144543766975403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5683823823928833},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5419548153877258},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5412715077400208},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4913877546787262},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42651355266571045},{"id":"https://openalex.org/keywords/warehouse","display_name":"Warehouse","score":0.4245927929878235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30068641901016235},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.19086021184921265},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14810711145401},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11990901827812195},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10270315408706665},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08888107538223267},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.08478495478630066},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0736333429813385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8144543766975403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5683823823928833},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5419548153877258},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5412715077400208},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4913877546787262},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42651355266571045},{"id":"https://openalex.org/C50416739","wikidata":"https://www.wikidata.org/wiki/Q181623","display_name":"Warehouse","level":2,"score":0.4245927929878235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30068641901016235},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.19086021184921265},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14810711145401},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11990901827812195},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10270315408706665},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08888107538223267},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.08478495478630066},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0736333429813385}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3579647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3579647","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1551562380","https://openalex.org/W1989407213","https://openalex.org/W2039107569","https://openalex.org/W2123030512","https://openalex.org/W2191404279","https://openalex.org/W2746553466","https://openalex.org/W2892258706","https://openalex.org/W2912609303","https://openalex.org/W2951278471","https://openalex.org/W2963658727","https://openalex.org/W2964997335","https://openalex.org/W2997536466","https://openalex.org/W3092786062","https://openalex.org/W3129616587","https://openalex.org/W3134901932","https://openalex.org/W3201099806","https://openalex.org/W3206082228","https://openalex.org/W4285102394","https://openalex.org/W4289656429","https://openalex.org/W4307934390","https://openalex.org/W4311127142","https://openalex.org/W4367727829","https://openalex.org/W4383112356","https://openalex.org/W4389689571","https://openalex.org/W6685444567","https://openalex.org/W6735641298","https://openalex.org/W6748554570","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6761920647","https://openalex.org/W6768539364","https://openalex.org/W6780078254","https://openalex.org/W6780316117","https://openalex.org/W6788085919"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Efficient":[0],"multi-agent":[1],"path":[2],"finding":[3],"(MAPF)":[4],"is":[5],"essential":[6],"for":[7],"large-scale":[8,55,116],"warehousing":[9],"and":[10,32,75,93,117],"logistics":[11],"systems.":[12],"Despite":[13],"the":[14,51,59,88,91],"potential":[15],"of":[16,90],"reinforcement":[17,45],"learning":[18,46,82],"(RL)":[19],"methods,":[20],"current":[21],"approaches":[22],"struggle":[23],"with":[24,136],"challenges":[25],"such":[26],"as":[27],"inefficient":[28],"exploration,":[29],"poor":[30],"generalization":[31],"inadequate":[33],"deadlock":[34,113],"resolution.":[35],"To":[36],"address":[37,50],"these":[38],"issues,":[39],"we":[40,101],"propose":[41],"a":[42,103],"novel":[43],"evolutionary":[44],"(ERL)":[47],"framework":[48,60,85],"to":[49,66,86,97,111],"MAPF":[52],"problem":[53],"in":[54,115,133],"warehouse":[56],"environments.":[57,99],"Specifically,":[58],"leverages":[61],"distributed":[62],"policy":[63,72,76,92],"evolution":[64],"methods":[65,127],"provide":[67],"diverse":[68],"experiences,":[69],"thereby":[70],"improving":[71],"training":[73],"efficiency":[74],"performance.":[77],"We":[78],"further":[79],"integrate":[80],"curriculum":[81],"into":[83],"this":[84],"improve":[87],"generality":[89],"make":[94],"it":[95],"scalable":[96],"larger":[98],"Additionally,":[100],"introduce":[102],"deadlock-breaking":[104],"mechanism":[105],"based":[106],"on":[107],"expert":[108],"experience,":[109],"helping":[110],"mitigate":[112],"issues":[114],"high-density":[118],"scenarios.":[119],"Experiments":[120],"show":[121],"that":[122],"our":[123],"method":[124],"outperforms":[125],"existing":[126],"across":[128],"various":[129],"environments,":[130],"particularly":[131],"excelling":[132],"complex":[134],"scenarios":[135],"over":[137],"1,000":[138],"agents.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}