{"id":"https://openalex.org/W4295855743","doi":"https://doi.org/10.23919/acc53348.2022.9867386","title":"Multi-Agent Stochastic Control using Path Integral Policy Improvement","display_name":"Multi-Agent Stochastic Control using Path Integral Policy Improvement","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4295855743","doi":"https://doi.org/10.23919/acc53348.2022.9867386"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867386","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867386","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-314464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079582182","display_name":"P\u00e9ter V\u00e1rnai","orcid":"https://orcid.org/0000-0002-7422-3966"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Peter Varnai","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055348953","display_name":"Dimos V. Dimarogonas","orcid":"https://orcid.org/0000-0001-7309-8086"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Dimos V. Dimarogonas","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079582182"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.4324,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47942158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"3406","last_page":"3411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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"}},{"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.7823360562324524},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.6757251024246216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6326213479042053},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.629751443862915},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5812199711799622},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5481238961219788},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5348061323165894},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4495472013950348},{"id":"https://openalex.org/keywords/path-integral-formulation","display_name":"Path integral formulation","score":0.4112865924835205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2601433992385864},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.21313941478729248},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20475292205810547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12935566902160645},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12184953689575195},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07837975025177002}],"concepts":[{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.7823360562324524},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.6757251024246216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326213479042053},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.629751443862915},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5812199711799622},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5481238961219788},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5348061323165894},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4495472013950348},{"id":"https://openalex.org/C154018700","wikidata":"https://www.wikidata.org/wiki/Q898323","display_name":"Path integral formulation","level":3,"score":0.4112865924835205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2601433992385864},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.21313941478729248},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20475292205810547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12935566902160645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12184953689575195},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07837975025177002},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc53348.2022.9867386","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867386","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-314464","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-314464","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-314464","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-314464","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W613360614","https://openalex.org/W1480347379","https://openalex.org/W2098524868","https://openalex.org/W2137808289","https://openalex.org/W2167697140","https://openalex.org/W2327668930","https://openalex.org/W2410617946","https://openalex.org/W2529601334","https://openalex.org/W2563595373","https://openalex.org/W2784309563","https://openalex.org/W2908261578","https://openalex.org/W2945523111","https://openalex.org/W2998415550","https://openalex.org/W3005581722","https://openalex.org/W3017666326","https://openalex.org/W3120610168","https://openalex.org/W3124086936","https://openalex.org/W3184157780","https://openalex.org/W4206633704","https://openalex.org/W4295855743","https://openalex.org/W6628707872","https://openalex.org/W6640290305","https://openalex.org/W6674872077"],"related_works":["https://openalex.org/W4285069850","https://openalex.org/W2891970004","https://openalex.org/W1996916724","https://openalex.org/W4240963716","https://openalex.org/W1974634278","https://openalex.org/W1596637634","https://openalex.org/W2321918740","https://openalex.org/W2154273227","https://openalex.org/W1776186222","https://openalex.org/W2900794160"],"abstract_inverted_index":{"Path":[0],"integral":[1],"policy":[2],"improvement":[3],"(PI":[4],"<sup":[5],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[6],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[7],")":[8],"is":[9],"a":[10,28,45,74,89,92],"data-driven":[11],"method":[12],"for":[13,95],"solving":[14],"stochastic":[15],"optimal":[16],"control":[17,50],"problems.":[18],"Both":[19],"feedforward":[20],"and":[21,37,91],"feedback":[22,98],"controls":[23],"are":[24,107],"calculated":[25],"based":[26],"on":[27],"sample":[29],"of":[30,34],"noisy":[31],"open-loop":[32],"trajectories":[33],"the":[35,58,63,70,97],"system":[36],"their":[38],"costs,":[39],"which":[40],"can":[41],"be":[42],"obtained":[43],"in":[44],"highly":[46],"parallelizable":[47],"manner.":[48],"The":[49,104],"strategy":[51],"offers":[52],"theoretical":[53,79,105],"performance":[54],"guarantees":[55,80],"related":[56],"to":[57,73],"expected":[59],"cost":[60],"achieved":[61],"by":[62],"resulting":[64],"closed-loop":[65],"system.":[66],"This":[67],"paper":[68],"extends":[69],"single-agent":[71],"case":[72],"multi-agent":[75],"setting,":[76],"where":[77],"such":[78],"have":[81],"not":[82],"been":[83],"attained":[84],"previously.":[85],"We":[86],"provide":[87],"both":[88],"decentralized":[90],"leader-follower":[93],"scheme":[94],"distributing":[96],"calculations":[99],"under":[100],"different":[101],"communication":[102],"constraints.":[103],"results":[106],"verified":[108],"numerically":[109],"through":[110],"simulations.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}