{"id":"https://openalex.org/W2601465345","doi":"https://doi.org/10.48550/arxiv.1703.03121","title":"Coordinated Multi-Agent Imitation Learning","display_name":"Coordinated Multi-Agent Imitation Learning","publication_year":2017,"publication_date":"2017-03-09","ids":{"openalex":"https://openalex.org/W2601465345","doi":"https://doi.org/10.48550/arxiv.1703.03121","mag":"2601465345"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.03121","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.03121","pdf_url":"https://arxiv.org/pdf/1703.03121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.03121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114594133","display_name":"Hoang M. Le","orcid":"https://orcid.org/0000-0001-9170-9581","observed_orcids":["https://orcid.org/0000-0001-9170-9581","https://orcid.org/0000-0002-5521-5856"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le, Hoang M.","raw_affiliation_strings":["California Institute of Technology, Pasadena CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena CA#TAB#","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085826758","display_name":"Yisong Yue","orcid":"https://orcid.org/0000-0001-9127-1989","observed_orcids":["https://orcid.org/0000-0001-9127-1989"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue, Yisong","raw_affiliation_strings":["California Institute of Technology, Pasadena CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena CA#TAB#","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111702500","display_name":"Peter Carr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carr, Peter","raw_affiliation_strings":["[Disney Research, Pittsburgh, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Disney Research, Pittsburgh, PA]","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032604032","display_name":"Patrick Lucey","orcid":"https://orcid.org/0009-0009-7864-3659","observed_orcids":["https://orcid.org/0009-0009-7864-3659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucey, Patrick","raw_affiliation_strings":["STATS LLC, Chicago, IL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STATS LLC, Chicago, IL#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1995","last_page":"2003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/team-sports","display_name":"team sports","score":0.6610000133514404},{"id":"https://openalex.org/keywords/team-strategy","display_name":"team strategy","score":0.6359999775886536},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7696691155433655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560720443725586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5977149605751038},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.537959098815918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4707287549972534},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4334973096847534},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10520008206367493},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1703.03121","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.03121","pdf_url":"https://arxiv.org/pdf/1703.03121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"pmh:oai:authors.library.caltech.edu:80920","doi":null,"is_oa":true,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20170829-143913716","pdf_url":"https://resolver.caltech.edu/CaltechAUTHORS:20170829-143913716","source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1703.03121","doi":"https://doi.org/10.48550/arxiv.1703.03121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.03121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2601465345","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1703.03121.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.03121","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.03121","pdf_url":"https://arxiv.org/pdf/1703.03121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G734129387","display_name":"AitF: Algorithmic challenges in smart grids: control, optimization & learning","funder_award_id":"1637598","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8816568891","display_name":"RI: Medium: CompCog: Automated Discovery of Macro-Variables from Raw Spatiotemporal Data","funder_award_id":"1564330","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/F4320308204","display_name":"Northrop Grumman","ror":"https://ror.org/05kewds18"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2601465345.pdf","grobid_xml":"https://content.openalex.org/works/W2601465345.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W96529184","https://openalex.org/W648786980","https://openalex.org/W1515851193","https://openalex.org/W1795258949","https://openalex.org/W1881594620","https://openalex.org/W1931877416","https://openalex.org/W1986065347","https://openalex.org/W2042581906","https://openalex.org/W2053913299","https://openalex.org/W2064675550","https://openalex.org/W2097482982","https://openalex.org/W2099618002","https://openalex.org/W2107544712","https://openalex.org/W2115979064","https://openalex.org/W2118318536","https://openalex.org/W2124271233","https://openalex.org/W2145494108","https://openalex.org/W2147492008","https://openalex.org/W2153066670","https://openalex.org/W2153159477","https://openalex.org/W2158349948","https://openalex.org/W2166851633","https://openalex.org/W2173183968","https://openalex.org/W2434014514","https://openalex.org/W2575967531","https://openalex.org/W2600812268","https://openalex.org/W2951004968","https://openalex.org/W2953030299","https://openalex.org/W3122781013","https://openalex.org/W6977390765"],"related_works":["https://openalex.org/W7161029312","https://openalex.org/W2945166833","https://openalex.org/W7100053072","https://openalex.org/W4401380542","https://openalex.org/W11035765","https://openalex.org/W4285605933","https://openalex.org/W7096028525","https://openalex.org/W3204358081","https://openalex.org/W2883057932","https://openalex.org/W4416378668"],"abstract_inverted_index":{"We":[0,46,75,108],"study":[1],"the":[2,36,60,77,104,117],"problem":[3,85],"of":[4,9,25,79,86,119],"imitation":[5,73,124],"learning":[6,21,70,87],"from":[7],"demonstrations":[8,37],"multiple":[10,88],"coordinating":[11],"agents.":[12],"One":[13],"key":[14],"challenge":[15],"in":[16,35,94,103],"this":[17],"setting":[18],"is":[19,32],"that":[20,51,110],"a":[22,43,48,54,83,112],"good":[23],"model":[24,57,114],"coordination":[26,31,56,113],"can":[27],"be":[28,40],"difficult,":[29],"since":[30],"often":[33],"implicit":[34],"and":[38],"must":[39],"inferred":[41],"as":[42],"latent":[44,55],"variable.":[45],"propose":[47],"joint":[49],"approach":[50,81],"simultaneously":[52],"learns":[53],"along":[58],"with":[59,71],"individual":[61],"policies.":[62],"In":[63],"particular,":[64],"our":[65,80],"method":[66],"integrates":[67],"unsupervised":[68],"structure":[69],"conventional":[72,128],"learning.":[74],"illustrate":[76],"power":[78],"on":[82],"difficult":[84],"policies":[89],"for":[90],"fine-grained":[91],"behavior":[92],"modeling":[93],"team":[95,106],"sports,":[96],"where":[97],"different":[98,101],"players":[99,120],"occupy":[100],"roles":[102,118],"coordinated":[105],"strategy.":[107],"show":[109],"having":[111],"to":[115,127],"infer":[116],"yields":[121],"substantially":[122],"improved":[123],"loss":[125],"compared":[126],"baselines.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-04-07T00:00:00"}