{"id":"https://openalex.org/W3100191104","doi":"https://doi.org/10.1109/iros51168.2021.9636344","title":"Scalable Reinforcement Learning Policies for Multi-Agent Control","display_name":"Scalable Reinforcement Learning Policies for Multi-Agent Control","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3100191104","doi":"https://doi.org/10.1109/iros51168.2021.9636344","mag":"3100191104"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636344","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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 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/A5032519592","display_name":"Christopher D. Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher D. Hsu","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068209902","display_name":"Heejin Jeong","orcid":"https://orcid.org/0000-0002-0122-532X"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heejin Jeong","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243115","display_name":"George J. Pappas","orcid":"https://orcid.org/0000-0001-9081-0637"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George J. Pappas","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006038667","display_name":"Pratik Chaudhari","orcid":"https://orcid.org/0000-0003-4590-1956"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Chaudhari","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032519592"],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":10.17,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98694138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4785","last_page":"4791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9886999726295471,"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":0.8562904000282288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8075492978096008},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7945883274078369},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.612310528755188},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6113298535346985},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.49674898386001587},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.49386268854141235},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.46042490005493164},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4580037593841553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3679371476173401},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36458203196525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3453383147716522}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8562904000282288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075492978096008},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7945883274078369},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.612310528755188},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6113298535346985},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.49674898386001587},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49386268854141235},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.46042490005493164},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4580037593841553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3679371476173401},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36458203196525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3453383147716522},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636344","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W26912726","https://openalex.org/W309675244","https://openalex.org/W1524674316","https://openalex.org/W1562003885","https://openalex.org/W1641379095","https://openalex.org/W1977455750","https://openalex.org/W2009318488","https://openalex.org/W2034725503","https://openalex.org/W2072931689","https://openalex.org/W2087988258","https://openalex.org/W2098774185","https://openalex.org/W2098846072","https://openalex.org/W2117709074","https://openalex.org/W2119792923","https://openalex.org/W2122950833","https://openalex.org/W2131887066","https://openalex.org/W2172933221","https://openalex.org/W2284854825","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2626778328","https://openalex.org/W2768629321","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2789525339","https://openalex.org/W2790514337","https://openalex.org/W2794643322","https://openalex.org/W2804155543","https://openalex.org/W2894976951","https://openalex.org/W2913295839","https://openalex.org/W2949650786","https://openalex.org/W2949963774","https://openalex.org/W2952433032","https://openalex.org/W2962232176","https://openalex.org/W2970879379","https://openalex.org/W2973525135","https://openalex.org/W2984872799","https://openalex.org/W2995520132","https://openalex.org/W3003775893","https://openalex.org/W3011985369","https://openalex.org/W3012445938","https://openalex.org/W3012934742","https://openalex.org/W3032554070","https://openalex.org/W3034971464","https://openalex.org/W3035829937","https://openalex.org/W3036295212","https://openalex.org/W3036931094","https://openalex.org/W3046086792","https://openalex.org/W3090030312","https://openalex.org/W3098851887","https://openalex.org/W3124420883","https://openalex.org/W4287774906","https://openalex.org/W4288090965","https://openalex.org/W4295113716","https://openalex.org/W4295598622","https://openalex.org/W4299285968","https://openalex.org/W4299802797","https://openalex.org/W4301311528","https://openalex.org/W4385245566","https://openalex.org/W6601103950","https://openalex.org/W6610855191","https://openalex.org/W6644807125","https://openalex.org/W6674884181","https://openalex.org/W6678203656","https://openalex.org/W6685388067","https://openalex.org/W6695796721","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6744580074","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6748929038","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6762491519","https://openalex.org/W6766224423","https://openalex.org/W6767205014","https://openalex.org/W6767919266","https://openalex.org/W6770566355","https://openalex.org/W6771904302","https://openalex.org/W6775529125","https://openalex.org/W6779416026","https://openalex.org/W6780252837","https://openalex.org/W6785173017"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2386410636","https://openalex.org/W3038962357"],"abstract_inverted_index":{"We":[0,40,129],"develop":[1,131],"a":[2,42,100,109,117,132],"Multi-Agent":[3],"Reinforcement":[4],"Learning":[5],"(MARL)":[6],"method":[7,17],"to":[8,34,49,73,85,98,116,155,163,174],"learn":[9],"scalable":[10],"control":[11,127],"policies":[12],"for":[13,30],"target":[14],"tracking.":[15],"Our":[16],"can":[18],"handle":[19,86],"an":[20,87],"arbitrary":[21,88],"number":[22,89],"of":[23,78,90,120,124,157,167,172,177],"pursuers":[24,36,51,113],"and":[25,58,103,144,153,170,179],"targets;":[26],"we":[27,104],"show":[28],"results":[29],"tasks":[31],"consisting":[32],"up":[33],"1000":[35,38],"tracking":[37],"targets.":[39,91,180],"use":[41],"decentralized,":[43],"partially-observable":[44],"Markov":[45],"Decision":[46],"Process":[47],"framework":[48],"model":[50],"as":[52],"agents":[53,178],"receiving":[54],"partial":[55],"observations":[56],"(range":[57],"bearing)":[59],"about":[60],"targets":[61],"which":[62],"move":[63],"using":[64],"fixed,":[65],"unknown":[66],"policies.":[67],"An":[68],"attention":[69],"mechanism":[70,82],"is":[71],"used":[72,97],"parameterize":[74],"the":[75,79,158,165,168],"value":[76],"function":[77],"agents;":[80],"this":[81],"allows":[83,136],"us":[84],"Entropy-regularized":[92],"off-policy":[93],"RL":[94],"methods":[95],"are":[96,161],"train":[99],"stochastic":[101],"policy,":[102],"discuss":[105],"how":[106],"it":[107],"enables":[108],"hedging":[110],"behavior":[111],"between":[112],"that":[114,135],"leads":[115],"weak":[118],"form":[119],"cooperation":[121],"in":[122],"spite":[123],"completely":[125],"decentralized":[126],"execution.":[128],"further":[130],"masking":[133],"heuristic":[134],"training":[137],"on":[138,146],"smaller":[139],"problems":[140],"with":[141],"few":[142],"pursuers-targets":[143],"execution":[145],"much":[147],"larger":[148],"problems.":[149],"Thorough":[150],"simulation":[151],"experiments":[152],"comparisons":[154],"state":[156],"art":[159],"algorithms":[160],"performed":[162],"study":[164],"scalability":[166],"approach":[169],"robustness":[171],"performance":[173],"varying":[175],"numbers":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}