{"id":"https://openalex.org/W7133336067","doi":"https://doi.org/10.1109/lra.2026.3669783","title":"Mean-Field Deep Reinforcement Learning for Multi-Agent Path Finding","display_name":"Mean-Field Deep Reinforcement Learning for Multi-Agent Path Finding","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133336067","doi":"https://doi.org/10.1109/lra.2026.3669783"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3669783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3669783","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/A5078343911","display_name":"Lin Huo","orcid":"https://orcid.org/0000-0002-6510-5212"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Huo","raw_affiliation_strings":["Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-6510-5212","affiliations":[{"raw_affiliation_string":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045037481","display_name":"Jianlin Mao","orcid":"https://orcid.org/0000-0003-1407-4863"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlin Mao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-1407-4863","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038213135","display_name":"Hongjun San","orcid":"https://orcid.org/0000-0002-4256-5582"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjun San","raw_affiliation_strings":["Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-4256-5582","affiliations":[{"raw_affiliation_string":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruiqi Li","orcid":"https://orcid.org/0000-0002-8934-8032"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Li","raw_affiliation_strings":["Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-8934-8032","affiliations":[{"raw_affiliation_string":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiwei Xuan","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xuan","raw_affiliation_strings":["Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24643896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"5278","last_page":"5285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.48030000925064087,"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":0.48030000925064087,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1615999937057495,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03530000150203705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8490999937057495},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6141999959945679},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6013000011444092},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5928999781608582},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4966999888420105},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3984000086784363},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.3874000012874603},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8490999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6193000078201294},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4966999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48019999265670776},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.31450000405311584},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3669783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3669783","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":[{"id":"https://openalex.org/G5205733978","display_name":null,"funder_award_id":"62263017","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2169528473","https://openalex.org/W2892258706","https://openalex.org/W2963809389","https://openalex.org/W2964997335","https://openalex.org/W3089506933","https://openalex.org/W3092786062","https://openalex.org/W3192815666","https://openalex.org/W3201002245","https://openalex.org/W4205985266","https://openalex.org/W4226146005","https://openalex.org/W4230008158","https://openalex.org/W4385068279","https://openalex.org/W4386511453","https://openalex.org/W4392909682","https://openalex.org/W4395451464","https://openalex.org/W4395466958","https://openalex.org/W4399261747","https://openalex.org/W4403210047","https://openalex.org/W4405785130","https://openalex.org/W4405812064","https://openalex.org/W4410234709","https://openalex.org/W4413157507"],"related_works":[],"abstract_inverted_index":{"Continuous-space":[0],"multi-agent":[1],"path":[2],"finding":[3],"(MAPF)":[4],"presents":[5],"severe":[6],"challenges":[7],"for":[8,80],"deep":[9],"reinforcement":[10],"learning":[11],"(DRL),":[12],"as":[13],"joint":[14],"state\u2013action":[15],"spaces":[16],"grow":[17],"exponentially":[18],"and":[19,72,112,140],"fine-grained":[20],"inter-agent":[21],"coordination":[22],"is":[23,101],"required.":[24],"Applying":[25],"mean-field":[26,61,67,85],"approximation":[27],"can":[28],"reduce":[29],"input":[30],"complexity":[31],"from$\\mathcal":[32],"{O}(N^{2}~d)$to$\\mathcal":[33],"{O}(Nd)$,":[34],"but":[35],"naively":[36],"averaging":[37],"neighbors":[38],"may":[39],"weaken":[40],"critical":[41],"local":[42,66],"interactions,":[43],"limiting":[44],"planning":[45,88],"success.":[46],"To":[47],"address":[48],"this,":[49],"we":[50],"propose":[51],"the":[52,113],"Mean-Field":[53],"Multi-Agent":[54],"Reinforcement":[55],"Pathfinding":[56],"Framework":[57],"(MAMFRPF),":[58],"which":[59],"integrates":[60],"interaction":[62],"compression,":[63],"a":[64,73],"dual-stream":[65,77],"critic,":[68],"trust-region":[69],"policy":[70,110],"optimization,":[71],"sparse-reward":[74,114],"design.":[75],"The":[76],"critic":[78],"compensates":[79],"information":[81],"loss":[82],"caused":[83],"by":[84,90,103,131],"averaging,":[86],"improving":[87],"success":[89,134],"over":[91],"20":[92],"percentage":[93],"points":[94],"under":[95],"partial":[96],"observability,":[97],"while":[98],"training":[99],"time":[100],"reduced":[102],"roughly":[104],"7%.":[105],"Trust-region":[106],"optimization":[107],"ensures":[108],"monotonic":[109],"improvement,":[111],"mechanism":[115],"accelerates":[116],"long-horizon":[117],"credit":[118],"assignment.":[119],"Experiments":[120],"on":[121],"continuous":[122],"MAPF":[123],"benchmarks":[124],"show":[125],"that":[126],"MAMFRPF":[127],"outperforms":[128],"strong":[129],"baselines":[130],"15%":[132],"in":[133],"rate,":[135],"scales":[136],"with":[137],"agent":[138],"density,":[139],"generalizes":[141],"across":[142],"diverse":[143],"spatial":[144],"layouts.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-04T00:00:00"}