{"id":"https://openalex.org/W2892258706","doi":"https://doi.org/10.1109/lra.2019.2903261","title":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","display_name":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","publication_year":2019,"publication_date":"2019-03-06","ids":{"openalex":"https://openalex.org/W2892258706","doi":"https://doi.org/10.1109/lra.2019.2903261","mag":"2892258706"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2019.2903261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2903261","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.03531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069667034","display_name":"Guillaume Sartoretti","orcid":"https://orcid.org/0000-0002-7579-9916"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guillaume Sartoretti","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022467361","display_name":"Justin Kerr","orcid":"https://orcid.org/0000-0002-0536-4853"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Kerr","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113923164","display_name":"Yunfei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunfei Shi","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031211737","display_name":"Glenn Wagner","orcid":"https://orcid.org/0000-0002-3450-398X"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Glenn Wagner","raw_affiliation_strings":["Commonwealth Scientific and Industrial Research Organisation, Pullenvale, QLD, Australia"],"affiliations":[{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organisation, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107677928","display_name":"T. K. Satish Kumar","orcid":"https://orcid.org/0000-0002-1748-8431"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. K. Satish Kumar","raw_affiliation_strings":["Computer Science Department, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026549557","display_name":"Sven Koenig","orcid":"https://orcid.org/0000-0002-5458-094X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sven Koenig","raw_affiliation_strings":["Computer Science Department, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048906141","display_name":"Howie Choset","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howie Choset","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069667034"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":18.6414,"has_fulltext":false,"cited_by_count":390,"citation_normalized_percentile":{"value":0.99395379,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"4","issue":"3","first_page":"2378","last_page":"2385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9990000128746033,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/pathfinding","display_name":"Pathfinding","score":0.8693180084228516},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7991766929626465},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6559778451919556},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6012030839920044},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4084581136703491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40579938888549805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3700753450393677},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3360890746116638},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.24406415224075317},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11674955487251282},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.05055984854698181},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.04442152380943298}],"concepts":[{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.8693180084228516},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7991766929626465},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6559778451919556},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6012030839920044},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4084581136703491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40579938888549805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700753450393677},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3360890746116638},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.24406415224075317},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11674955487251282},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.05055984854698181},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.04442152380943298},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2019.2903261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2903261","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"},{"id":"pmh:oai:arXiv.org:1809.03531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.03531","pdf_url":"https://arxiv.org/pdf/1809.03531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.03531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.03531","pdf_url":"https://arxiv.org/pdf/1809.03531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G5118135302","display_name":null,"funder_award_id":"1837779","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G542566607","display_name":null,"funder_award_id":"1817189","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6861119503","display_name":null,"funder_award_id":"1724392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8978827964","display_name":null,"funder_award_id":"1409987","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306185","display_name":"Richard King Mellon Foundation","ror":"https://ror.org/03qevzg44"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W3359552","https://openalex.org/W90946604","https://openalex.org/W192919555","https://openalex.org/W206679605","https://openalex.org/W1424654272","https://openalex.org/W1488757178","https://openalex.org/W1542670833","https://openalex.org/W1551562380","https://openalex.org/W1686810756","https://openalex.org/W1926863402","https://openalex.org/W1931877416","https://openalex.org/W1971890413","https://openalex.org/W1980353316","https://openalex.org/W1989407213","https://openalex.org/W1990186220","https://openalex.org/W2021042867","https://openalex.org/W2030775133","https://openalex.org/W2039107569","https://openalex.org/W2058094241","https://openalex.org/W2100695938","https://openalex.org/W2121863487","https://openalex.org/W2123030512","https://openalex.org/W2133067819","https://openalex.org/W2144855002","https://openalex.org/W2166462345","https://openalex.org/W2194775991","https://openalex.org/W2201581102","https://openalex.org/W2294562513","https://openalex.org/W2313835963","https://openalex.org/W2395575420","https://openalex.org/W2541273873","https://openalex.org/W2611243847","https://openalex.org/W2617547828","https://openalex.org/W2741122588","https://openalex.org/W2768629321","https://openalex.org/W2785379783","https://openalex.org/W2891052160","https://openalex.org/W2903382683","https://openalex.org/W2903998385","https://openalex.org/W2913845934","https://openalex.org/W2950395671","https://openalex.org/W2962938168","https://openalex.org/W2962957031","https://openalex.org/W2963000099","https://openalex.org/W2963099939","https://openalex.org/W2963363446","https://openalex.org/W2963407617","https://openalex.org/W2963411833","https://openalex.org/W2963477884","https://openalex.org/W2963809389","https://openalex.org/W2964043796","https://openalex.org/W4214717370","https://openalex.org/W4244044799","https://openalex.org/W4299802797","https://openalex.org/W4312258073","https://openalex.org/W6600116910","https://openalex.org/W6629161821","https://openalex.org/W6632973643","https://openalex.org/W6637373629","https://openalex.org/W6640174482","https://openalex.org/W6640227988","https://openalex.org/W6675090247","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6729318774","https://openalex.org/W6735579001","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6744563498","https://openalex.org/W6744564315","https://openalex.org/W6748314335","https://openalex.org/W6757107679","https://openalex.org/W6757123219"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4285687848"],"abstract_inverted_index":{"Multi-agent":[0],"path":[1],"finding":[2],"(MAPF)":[3],"is":[4,62],"an":[5,122],"essential":[6],"component":[7],"of":[8,115,121,148,190],"many":[9],"large-scale,":[10],"real-world":[11],"robot":[12],"deployments,":[13,50],"from":[14],"aerial":[15],"swarms":[16],"to":[17,48,70,86,153,168],"warehouse":[18],"automation.":[19],"However,":[20],"despite":[21],"the":[22,139,183],"community's":[23],"continued":[24],"efforts,":[25],"most":[26],"state-of-the-art":[27,176],"MAPF":[28,79,124,177],"planners":[29],"still":[30],"rely":[31],"on":[32,112,163],"centralized":[33],"planning":[34,44,65],"and":[35,53,83,134,150,157,171,198],"scale":[36],"poorly":[37],"past":[38],"a":[39,75,98,187,191],"few":[40],"hundred":[41],"agents.":[42],"Such":[43],"approaches":[45],"are":[46,67],"maladapted":[47],"realworld":[49],"where":[51,91],"noise":[52],"uncertainty":[54],"often":[55],"require":[56],"paths":[57,95],"be":[58,143],"recomputed":[59],"online,":[60],"which":[61],"impossible":[63],"when":[64],"times":[66],"in":[68,97,186],"seconds":[69],"minutes.":[71],"We":[72,160],"present":[73,161],"PRIMAL,":[74],"novel":[76],"framework":[77,107],"for":[78],"that":[80],"combines":[81],"reinforcement":[82],"imitation":[84],"learning":[85,114],"teach":[87],"fully":[88],"decentralized":[89],"policies,":[90],"agents":[92,149,170],"reactively":[93],"plan":[94],"online":[96],"partially":[99],"observable":[100],"world":[101,158,197],"while":[102],"exhibiting":[103],"implicit":[104],"coordination.":[105],"This":[106],"extends":[108],"our":[109],"previous":[110],"work":[111],"distributed":[113],"collaborative":[116],"policies":[117,185],"by":[118],"introducing":[119],"demonstrations":[120],"expert":[123],"planner":[125],"during":[126],"training,":[127],"as":[128,130],"well":[129],"careful":[131],"reward":[132],"shaping":[133],"environment":[135],"sampling.":[136],"Once":[137],"learned,":[138],"resulting":[140],"policy":[141],"can":[142],"copied":[144],"onto":[145],"any":[146],"number":[147],"naturally":[151],"scales":[152],"different":[154],"team":[155],"sizes":[156],"dimensions.":[159],"results":[162],"randomized":[164],"worlds":[165],"with":[166],"up":[167],"1024":[169],"compare":[172],"success":[173],"rates":[174],"against":[175],"planners.":[178],"Finally,":[179],"we":[180],"experimentally":[181],"validate":[182],"learned":[184],"hybrid":[188],"simulation":[189],"factory":[192],"mockup,":[193],"involving":[194],"both":[195],"real":[196],"simulated":[199],"robots.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":100},{"year":2024,"cited_by_count":86},{"year":2023,"cited_by_count":63},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}