{"id":"https://openalex.org/W4210280190","doi":"https://doi.org/10.1109/cdc45484.2021.9683740","title":"Imitation Learning From Inconcurrent Multi-Agent Interactions","display_name":"Imitation Learning From Inconcurrent Multi-Agent Interactions","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210280190","doi":"https://doi.org/10.1109/cdc45484.2021.9683740"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683740","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th 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/A5100327554","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0003-0289-1452"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013900180","display_name":"Weixiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixiao Huang","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630059","display_name":"Yanhua Li","orcid":"https://orcid.org/0000-0001-8972-503X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhua Li","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048686150","display_name":"Renjie Liao","orcid":"https://orcid.org/0009-0001-1660-9959"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Renjie Liao","raw_affiliation_strings":["University of Toronto and Vector Institute, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto and Vector Institute, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048506332","display_name":"Ziming Zhang","orcid":"https://orcid.org/0000-0002-0921-8298"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziming Zhang","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100327554"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.21340437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9805999994277954,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7461084723472595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246174216270447},{"id":"https://openalex.org/keywords/subgame-perfect-equilibrium","display_name":"Subgame perfect equilibrium","score":0.6782682538032532},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6246622800827026},{"id":"https://openalex.org/keywords/markov-perfect-equilibrium","display_name":"Markov perfect equilibrium","score":0.5938965678215027},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5529499053955078},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5279592275619507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4912795424461365},{"id":"https://openalex.org/keywords/subgame","display_name":"Subgame","score":0.490788072347641},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45641499757766724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45387381315231323},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4445219039916992},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.39772069454193115},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.284379780292511},{"id":"https://openalex.org/keywords/epsilon-equilibrium","display_name":"Epsilon-equilibrium","score":0.18479639291763306},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14127978682518005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11661672592163086},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08943796157836914},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07464563846588135},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07342782616615295}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7461084723472595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246174216270447},{"id":"https://openalex.org/C175983524","wikidata":"https://www.wikidata.org/wiki/Q1615834","display_name":"Subgame perfect equilibrium","level":3,"score":0.6782682538032532},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6246622800827026},{"id":"https://openalex.org/C67091656","wikidata":"https://www.wikidata.org/wiki/Q6771328","display_name":"Markov perfect equilibrium","level":3,"score":0.5938965678215027},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5529499053955078},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5279592275619507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4912795424461365},{"id":"https://openalex.org/C13576547","wikidata":"https://www.wikidata.org/wiki/Q3965283","display_name":"Subgame","level":5,"score":0.490788072347641},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45641499757766724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45387381315231323},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4445219039916992},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.39772069454193115},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.284379780292511},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.18479639291763306},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14127978682518005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11661672592163086},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08943796157836914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07464563846588135},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07342782616615295},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683740","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1496590343","https://openalex.org/W1540685400","https://openalex.org/W1542941925","https://openalex.org/W1605142459","https://openalex.org/W1626977535","https://openalex.org/W1771410628","https://openalex.org/W1999874108","https://openalex.org/W2048363324","https://openalex.org/W2051228319","https://openalex.org/W2098774185","https://openalex.org/W2125326611","https://openalex.org/W2141076336","https://openalex.org/W2142641780","https://openalex.org/W2147544021","https://openalex.org/W2164433993","https://openalex.org/W2257979135","https://openalex.org/W2462906003","https://openalex.org/W2749928749","https://openalex.org/W2883057932","https://openalex.org/W2946233467","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W3003540860","https://openalex.org/W3100866575","https://openalex.org/W4252284432","https://openalex.org/W4299802797","https://openalex.org/W6627932998","https://openalex.org/W6632235069","https://openalex.org/W6636868823","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6680724558","https://openalex.org/W6681478256","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6738796088","https://openalex.org/W6743802245","https://openalex.org/W6753207554","https://openalex.org/W6763248972"],"related_works":["https://openalex.org/W4282813745","https://openalex.org/W3122548660","https://openalex.org/W4309911979","https://openalex.org/W3124025958","https://openalex.org/W3142896253","https://openalex.org/W1598443623","https://openalex.org/W1595005794","https://openalex.org/W2125603368","https://openalex.org/W2099803346","https://openalex.org/W2000358093"],"abstract_inverted_index":{"Multi-agent":[0],"imitation":[1,62],"learning":[2,63],"(MA-IL)":[3],"aims":[4],"to":[5,75,94],"inversely":[6],"learn":[7],"policies":[8,72],"for":[9,35,42,65],"all":[10],"agents":[11,46],"using":[12,109],"demonstrations":[13],"collected":[14,113],"from":[15,114],"an":[16],"expert":[17,107],"group.":[18],"However,":[19],"this":[20,54],"problem":[21],"has":[22],"only":[23],"been":[24],"studied":[25],"in":[26,50],"the":[27,103],"setting":[28],"of":[29,105],"Markov":[30,68],"games":[31],"(MGs)":[32],"allowing":[33],"participants":[34],"concurrent":[36],"actions,":[37],"and":[38],"do":[39],"not":[40],"work":[41],"general":[43,66],"MGs,":[44],"with":[45],"inconcurrently":[47],"making":[48],"decisions":[49],"different":[51],"turns.":[52],"In":[53],"work,":[55],"we":[56],"propose":[57],"iMA-IL,":[58],"a":[59,81],"novel":[60],"multi-agent":[61],"framework":[64],"(inconcurrent)":[67],"games.":[69],"The":[70,88],"learned":[71],"are":[73],"proven":[74],"guarantee":[76],"subgame":[77],"perfect":[78],"equilibrium":[79,83,86],"(SPE),":[80],"stronger":[82],"than":[84],"Nash":[85],"(NE).":[87],"experiment":[89],"results":[90],"demonstrate":[91],"that":[92],"compared":[93],"state-of-the-art":[95],"baselines,":[96],"our":[97],"iMA-IL":[98],"model":[99],"can":[100],"better":[101],"infer":[102],"policy":[104],"each":[106],"agent":[108],"their":[110],"demonstration":[111],"data":[112],"inconcurrent":[115],"decision-making":[116],"scenarios.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}