{"id":"https://openalex.org/W4413917448","doi":"https://doi.org/10.1109/icra55743.2025.11128370","title":"Multi-Agent Inverse Q-Learning from Demonstrations","display_name":"Multi-Agent Inverse Q-Learning from Demonstrations","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917448","doi":"https://doi.org/10.1109/icra55743.2025.11128370"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5119514436","display_name":"Nathaniel Haynam","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathaniel Haynam","raw_affiliation_strings":["UC Berkeley,Electrical Engineering and Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Electrical Engineering and Computer Sciences","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094087260","display_name":"Adam Khoja","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Khoja","raw_affiliation_strings":["UC Berkeley,Electrical Engineering and Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Electrical Engineering and Computer Sciences","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780534","display_name":"Dhruv Kumar","orcid":"https://orcid.org/0000-0003-4831-1847"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Kumar","raw_affiliation_strings":["UC Berkeley,Electrical Engineering and Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Electrical Engineering and Computer Sciences","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057846593","display_name":"Vivek Myers","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Myers","raw_affiliation_strings":["UC Berkeley,Electrical Engineering and Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Electrical Engineering and Computer Sciences","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031426401","display_name":"Erdem B\u0131y\u0131k","orcid":"https://orcid.org/0000-0002-9516-3130"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erdem Biyik","raw_affiliation_strings":["UC Berkeley,Electrical Engineering and Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Electrical Engineering and Computer Sciences","institution_ids":["https://openalex.org/I134446601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119514436"],"corresponding_institution_ids":["https://openalex.org/I134446601"],"apc_list":null,"apc_paid":null,"fwci":1.8503,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88862893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"15021","last_page":"15028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9569000005722046,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9569000005722046,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9186000227928162,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9053999781608582,"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/computer-science","display_name":"Computer science","score":0.6025725603103638},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5943999886512756},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5500291585922241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3206004500389099},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1555575430393219},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.08815094828605652},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07227751612663269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025725603103638},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5500291585922241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3206004500389099},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1555575430393219},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.08815094828605652},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07227751612663269}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2169498096","https://openalex.org/W2991046523","https://openalex.org/W3040033967","https://openalex.org/W3109732654","https://openalex.org/W3174761862","https://openalex.org/W3197594072","https://openalex.org/W4210280190","https://openalex.org/W4285202401","https://openalex.org/W4306317350","https://openalex.org/W4323275929","https://openalex.org/W4381243977","https://openalex.org/W4381733136","https://openalex.org/W4382239238","https://openalex.org/W4387172060"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"When":[0],"reward":[1,12,44,179],"functions":[2],"are":[3],"hand-designed,":[4],"deep":[5],"reinforcement":[6,32],"learning":[7,33],"algorithms":[8,82],"often":[9,182],"suffer":[10],"from":[11,46,99,155],"misspecification,":[13],"causing":[14],"them":[15],"to":[16,37,63,148],"learn":[17],"suboptimal":[18],"policies":[19,129],"in":[20,50,76,130,173],"terms":[21],"of":[22,127],"the":[23,28,43,55,118,131,156],"intended":[24],"task":[25],"objectives.":[26,89],"In":[27],"single-agent":[29,143,157],"case,":[30],"inverse":[31],"(IRL)":[34],"techniques":[35],"attempt":[36],"address":[38,91],"this":[39],"issue":[40],"by":[41,181],"inferring":[42],"function":[45],"expert":[47],"demonstrations.":[48],"However,":[49],"multi-agent":[51,77,80,107,132,171],"problems,":[52],"misalignment":[53],"between":[54,138],"learned":[56],"and":[57,67,87,142,178],"true":[58],"objectives":[59],"is":[60],"exacerbated":[61],"due":[62],"increased":[64],"environment":[65],"non-stationarity":[66],"variance":[68],"that":[69],"scales":[70],"with":[71],"multiple":[72],"agents.":[73],"As":[74],"such,":[75],"general-sum":[78],"games,":[79],"IRL":[81],"have":[83],"difficulty":[84],"balancing":[85],"cooperative":[86],"competitive":[88],"To":[90],"these":[92],"issues,":[93],"we":[94],"propose":[95],"Multi-Agent":[96],"Marginal":[97],"Q-Learning":[98],"Demon-strations":[100],"(MAMQL),":[101],"a":[102,114,124,136,150],"novel":[103],"sample-efficient":[104],"framework":[105],"for":[106,123],"IRL.":[108],"For":[109],"each":[110],"agent,":[111],"MAMQL":[112,167],"learns":[113],"critic":[115],"marginalized":[116,140],"over":[117],"other":[119],"agents'":[120],"policies,":[121],"allowing":[122,146],"well-motivated":[125],"use":[126],"Boltzmann":[128],"context.":[133],"We":[134,186],"identify":[135],"connection":[137],"optimal":[139],"critics":[141],"soft-Q":[144],"IRL,":[145],"us":[147],"apply":[149],"direct,":[151],"simple":[152],"optimization":[153],"criterion":[154],"domain.":[158],"Across":[159],"our":[160,188],"experiments":[161],"on":[162],"three":[163],"different":[164],"simulated":[165],"domains,":[166],"significantly":[168],"outperforms":[169],"previous":[170],"methods":[172],"average":[174],"reward,":[175],"sample":[176],"efficiency,":[177],"recovery":[180],"more":[183],"than":[184],"2-5x.":[185],"make":[187],"code":[189],"available":[190],"at":[191],"https://sites.google.com/view/mamq/.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}