{"id":"https://openalex.org/W3045521901","doi":"https://doi.org/10.23919/acc45564.2020.9147704","title":"Automata Guided Semi-Decentralized Multi-Agent Reinforcement Learning","display_name":"Automata Guided Semi-Decentralized Multi-Agent Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045521901","doi":"https://doi.org/10.23919/acc45564.2020.9147704","mag":"3045521901"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147704","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051533554","display_name":"Chuangchuang Sun","orcid":"https://orcid.org/0000-0003-3049-5828"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuangchuang Sun","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375319","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0003-0214-0130"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":["Department of Mechanical Engineering, Boston University, Brookline, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Boston University, Brookline, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742095","display_name":"C\u0103lin Belta","orcid":"https://orcid.org/0000-0002-7141-2657"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calin Belta","raw_affiliation_strings":["Department of Mechanical Engineering, Boston University, Brookline, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Boston University, Brookline, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.46,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64283225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3900","last_page":"3905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10142","display_name":"Formal Methods in Verification","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9901999831199646,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8458408713340759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.765203595161438},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6348941922187805},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5292659997940063},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.46228766441345215},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4538109302520752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44281813502311707},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.4257374405860901},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4248647093772888},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39613136649131775},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35329920053482056},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3467748165130615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1185118556022644}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8458408713340759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765203595161438},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6348941922187805},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5292659997940063},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.46228766441345215},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4538109302520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44281813502311707},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.4257374405860901},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4248647093772888},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39613136649131775},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35329920053482056},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3467748165130615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1185118556022644},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc45564.2020.9147704","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1518116197","https://openalex.org/W1968254796","https://openalex.org/W1973039793","https://openalex.org/W1974812331","https://openalex.org/W2022750663","https://openalex.org/W2085366587","https://openalex.org/W2104602264","https://openalex.org/W2116399160","https://openalex.org/W2118318536","https://openalex.org/W2142924305","https://openalex.org/W2289025432","https://openalex.org/W2404361084","https://openalex.org/W2563184172","https://openalex.org/W2567705466","https://openalex.org/W2592045034","https://openalex.org/W2890179775","https://openalex.org/W2911097698","https://openalex.org/W4299802797","https://openalex.org/W6672070530","https://openalex.org/W6675811377","https://openalex.org/W6677254318","https://openalex.org/W6677834374","https://openalex.org/W6738796088","https://openalex.org/W6754491778"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,29,38,62,68,91,95,104,127,131,144,149,154,167,170,177,180,185],"problem":[4],"of":[5,67,93,151,179],"deploying":[6],"a":[7,12,85,135,157],"multi-robot":[8],"team":[9],"to":[10,28,60,81,89,109,142,165],"satisfy":[11],"syntactically":[13],"co-safe":[14],"Truncated":[15],"Linear":[16],"Temporal":[17],"Logic":[18],"(scTLTL)":[19],"task":[20,39,63],"specification":[21,97],"via":[22],"multi-agent":[23,182],"Reinforcement":[24],"Learning":[25],"(MARL).":[26],"Due":[27],"heterogeneous":[30],"agents":[31,80],"considered":[32],"here,":[33],"typical":[34],"approaches":[35],"cannot":[36],"avoid":[37],"assignment":[40,64],"problem,":[41],"which":[42],"is":[43,57,87,121,140,163,187],"inherently":[44],"difficult":[45],"and":[46,84,147],"can":[47],"sacrifice":[48],"optimality":[49],"(e.g.,":[50],"shortest":[51],"path)":[52],"through":[53],"manual":[54],"manipulation.":[55],"scTLTL":[56,96],"exploited":[58],"here":[59],"eliminate":[61],"as":[65],"part":[66],"learning":[69],"process.":[70],"MARL":[71],"usually":[72],"requires":[73],"some":[74],"direct":[75],"or":[76],"indirect":[77],"coordination":[78],"among":[79],"promote":[82],"convergence":[83],"tracker":[86],"needed":[88],"track":[90],"progress":[92],"satisfying":[94,153],"given":[98],"its":[99],"temporal":[100],"nature.":[101],"We":[102],"use":[103],"Finite":[105],"State":[106],"Automaton":[107],"(FSA)":[108],"address":[110],"these":[111],"two":[112],"issues.":[113],"An":[114],"FSA":[115,128,171],"augmented":[116,172],"Markov":[117],"Decision":[118],"Process":[119],"(MDP)":[120],"constructed":[122],"with":[123],"each":[124],"agent":[125],"sharing":[126],"state":[129],"carrying":[130],"global":[132],"information.":[133],"Moreover,":[134],"metric":[136],"called":[137],"robustness":[138],"degree":[139],"employed":[141],"replace":[143],"Boolean":[145],"semantics":[146],"quantify":[148],"reward":[150],"gradually":[152],"scTLTL.":[155],"Consequently,":[156],"language":[158],"guided":[159],"semi-decentralized":[160,181],"Q-learning":[161,183],"algorithm":[162],"proposed":[164],"maximize":[166],"return":[168],"over":[169],"MDP.":[173],"Simulation":[174],"results":[175],"demonstrate":[176],"effectiveness":[178],"while":[184],"complexity":[186],"significantly":[188],"reduced.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}