{"id":"https://openalex.org/W4405785295","doi":"https://doi.org/10.1109/iros58592.2024.10802293","title":"MFC-EQ: Mean-Field Control with Envelope Q-learning for Moving Decentralized Agents in Formation","display_name":"MFC-EQ: Mean-Field Control with Envelope Q-learning for Moving Decentralized Agents in Formation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785295","doi":"https://doi.org/10.1109/iros58592.2024.10802293"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101174812","display_name":"Qiushi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qiushi Lin","raw_affiliation_strings":["Simon Fraser University,School of Computing Science,Burnaby,BC,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Computing Science,Burnaby,BC,Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024389928","display_name":"Hang Ma","orcid":"https://orcid.org/0000-0002-0602-0999"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hang Ma","raw_affiliation_strings":["Simon Fraser University,School of Computing Science,Burnaby,BC,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Computing Science,Burnaby,BC,Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20713427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14156","last_page":"14163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8820000290870667,"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/T10320","display_name":"Neural Networks and Applications","score":0.8820000290870667,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8090999722480774,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.7885000109672546,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/envelope","display_name":"Envelope (radar)","score":0.7415420413017273},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7051215767860413},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5237008333206177},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46313101053237915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.390497624874115},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39041343331336975},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.32886698842048645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23594826459884644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19893890619277954},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.16165459156036377},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14544227719306946},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.09467408061027527}],"concepts":[{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.7415420413017273},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7051215767860413},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5237008333206177},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46313101053237915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.390497624874115},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39041343331336975},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.32886698842048645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23594826459884644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19893890619277954},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.16165459156036377},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14544227719306946},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.09467408061027527},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1542941925","https://openalex.org/W1988210060","https://openalex.org/W1989407213","https://openalex.org/W1998649829","https://openalex.org/W2039094757","https://openalex.org/W2042872950","https://openalex.org/W2060846151","https://openalex.org/W2081631327","https://openalex.org/W2117428849","https://openalex.org/W2169673701","https://openalex.org/W2186820913","https://openalex.org/W2296073425","https://openalex.org/W2593781315","https://openalex.org/W2892258706","https://openalex.org/W2964997335","https://openalex.org/W3004325772","https://openalex.org/W3037139179","https://openalex.org/W3088197938","https://openalex.org/W3094845617","https://openalex.org/W3129616587","https://openalex.org/W3201099806","https://openalex.org/W3206082228","https://openalex.org/W4221155367","https://openalex.org/W4293253503","https://openalex.org/W4379622577","https://openalex.org/W4383112356","https://openalex.org/W4389689571","https://openalex.org/W4401414215","https://openalex.org/W6632662516","https://openalex.org/W6674628981","https://openalex.org/W6677067356","https://openalex.org/W6677477198","https://openalex.org/W6732454287","https://openalex.org/W6744401026","https://openalex.org/W6747941106","https://openalex.org/W6754554871","https://openalex.org/W6758754608","https://openalex.org/W6766805167","https://openalex.org/W6766952794","https://openalex.org/W6788318589"],"related_works":["https://openalex.org/W2073227694","https://openalex.org/W2983473129","https://openalex.org/W1982160337","https://openalex.org/W1971380437","https://openalex.org/W1983548084","https://openalex.org/W2141691317","https://openalex.org/W2110846987","https://openalex.org/W2415097577","https://openalex.org/W2320718078","https://openalex.org/W2653530212"],"abstract_inverted_index":{"We":[0,119],"study":[1],"a":[2,11,36,80,94,108,131],"decentralized":[3],"version":[4],"of":[5,13,29,47,61,71,123,141],"Moving":[6],"Agents":[7],"in":[8],"Formation":[9],"(MAiF),":[10],"variant":[12],"Multi-Agent":[14],"Path":[15],"Finding":[16],"aiming":[17],"to":[18],"plan":[19],"collision-free":[20],"paths":[21],"for":[22,89,114],"multiple":[23],"agents":[24,40,125],"with":[25,68,104],"the":[26,58,69,74,121,162],"dual":[27],"objectives":[28,44,92],"reaching":[30],"their":[31],"goals":[32],"quickly":[33],"while":[34,129],"maintaining":[35],"desired":[37,163],"formation.":[38],"The":[39,53],"must":[41],"balance":[42],"these":[43,90],"under":[45],"conditions":[46],"partial":[48],"observation":[49],"and":[50,110],"limited":[51],"communication.":[52],"formation":[54,164],"maintenance":[55],"depends":[56],"on":[57],"joint":[59],"state":[60],"all":[62,124],"agents,":[63,72],"whose":[64],"dimensionality":[65],"increases":[66],"exponentially":[67],"number":[70],"rendering":[73],"learning":[75,79,112,130],"process":[76],"intractable.":[77],"Additionally,":[78],"single":[81],"policy":[82,134],"that":[83,147,168],"can":[84],"accommodate":[85],"different":[86],"linear":[87],"preferences":[88],"two":[91],"presents":[93],"significant":[95],"challenge.":[96],"In":[97],"this":[98,115],"paper,":[99],"we":[100],"propose":[101],"Mean-Field":[102],"Control":[103],"Envelop":[105],"Q-learning":[106],"(MFC-EQ),":[107],"scalable":[109],"adaptable":[111],"framework":[113],"bi-objective":[116],"multi-agent":[117],"problem.":[118],"approximate":[120],"dynamics":[122],"using":[126],"mean-field":[127],"theory":[128],"universal":[132],"preference-agnostic":[133],"through":[135],"envelop":[136],"Q-learning.":[137],"Our":[138],"empirical":[139],"evaluation":[140],"MFC-EQ":[142,155],"across":[143],"numerous":[144],"instances":[145],"shows":[146],"it":[148],"outperforms":[149],"state-of-the-art":[150],"centralized":[151],"MAiF":[152,170],"baselines.":[153],"Furthermore,":[154],"effectively":[156],"handles":[157],"more":[158],"complex":[159],"scenarios":[160],"where":[161],"changes":[165],"dynamically\u2014a":[166],"challenge":[167],"existing":[169],"planners":[171],"cannot":[172],"address.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}