{"id":"https://openalex.org/W3132069826","doi":"https://doi.org/10.1109/iros45743.2020.9341303","title":"Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph","display_name":"Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3132069826","doi":"https://doi.org/10.1109/iros45743.2020.9341303","mag":"3132069826"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5051533554","display_name":"Chuangchuang Sun","orcid":"https://orcid.org/0000-0003-3049-5828"},"institutions":[{"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":true,"raw_author_name":"Chuangchuang Sun","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040251822","display_name":"Macheng Shen","orcid":"https://orcid.org/0000-0002-1440-6904"},"institutions":[{"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":"Macheng Shen","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"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":"Jonathan P. How","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051533554"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88743301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11755","last_page":"11762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9764000177383423,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7984452247619629},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.671811044216156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6685891151428223},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5549255609512329},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5092812776565552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45349088311195374},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.44981151819229126},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4255019426345825},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4190242290496826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.291964054107666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1650044023990631}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7984452247619629},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.671811044216156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685891151428223},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5549255609512329},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5092812776565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45349088311195374},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.44981151819229126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4255019426345825},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4190242290496826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.291964054107666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1650044023990631},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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":65,"referenced_works":["https://openalex.org/W19838944","https://openalex.org/W115015868","https://openalex.org/W854541894","https://openalex.org/W1554960070","https://openalex.org/W1977655452","https://openalex.org/W2053081145","https://openalex.org/W2088956500","https://openalex.org/W2099618002","https://openalex.org/W2145339207","https://openalex.org/W2149469814","https://openalex.org/W2168977355","https://openalex.org/W2253795368","https://openalex.org/W2257979135","https://openalex.org/W2588790649","https://openalex.org/W2604314403","https://openalex.org/W2617547828","https://openalex.org/W2619122421","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2785315072","https://openalex.org/W2807741983","https://openalex.org/W2890904175","https://openalex.org/W2894976951","https://openalex.org/W2896451037","https://openalex.org/W2948342290","https://openalex.org/W2962232176","https://openalex.org/W2962839844","https://openalex.org/W2962938168","https://openalex.org/W2962966033","https://openalex.org/W2963039558","https://openalex.org/W2963123301","https://openalex.org/W2963403868","https://openalex.org/W2963407617","https://openalex.org/W2963502387","https://openalex.org/W2963588154","https://openalex.org/W2964290105","https://openalex.org/W2970777192","https://openalex.org/W3031321468","https://openalex.org/W3093287223","https://openalex.org/W4288336223","https://openalex.org/W4289363497","https://openalex.org/W4295598622","https://openalex.org/W4299285968","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6684660688","https://openalex.org/W6691766336","https://openalex.org/W6738577479","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6747941106","https://openalex.org/W6749304979","https://openalex.org/W6751674603","https://openalex.org/W6752380930","https://openalex.org/W6754700188","https://openalex.org/W6755069753","https://openalex.org/W6755542948","https://openalex.org/W6755662481","https://openalex.org/W6763173156","https://openalex.org/W6766224423","https://openalex.org/W7030590185"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W4306904969","https://openalex.org/W2347897961","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855"],"abstract_inverted_index":{"The":[0],"complexity":[1],"of":[2,60,136],"multiagent":[3,8,28,171],"reinforcement":[4],"learning":[5],"(MARL)":[6],"in":[7,26,34,92,114],"systems":[9],"increases":[10],"exponentially":[11],"with":[12,142],"respect":[13],"to":[14,126],"the":[15,42,61,110,130,134,137],"agent":[16],"number.":[17],"This":[18],"scalability":[19],"issue":[20],"prevents":[21],"MARL":[22,35,93,138],"from":[23,58],"being":[24],"applied":[25],"large-scale":[27,170],"systems.":[29],"However,":[30],"one":[31],"critical":[32],"feature":[33],"that":[36,41,128,149],"is":[37,40,94,140],"often":[38],"neglected":[39],"interactions":[43],"between":[44],"agents":[45,62,111,127],"are":[46],"quite":[47],"sparse.":[48],"Without":[49],"exploiting":[50],"this":[51,72,102,107],"sparsity":[52,108],"structure,":[53,109],"existing":[54],"works":[55,161],"aggregate":[56],"information":[57],"all":[59],"and":[63,132,158],"thus":[64,133],"have":[65],"a":[66,83,88,163,169],"high":[67],"sample":[68],"complexity.":[69],"To":[70],"address":[71],"issue,":[73],"we":[74],"propose":[75],"an":[76,115,154],"adaptive":[77],"sparse":[78,89,156],"attention":[79,104],"mechanism":[80],"by":[81,96,162],"generalizing":[82],"sparsity-inducing":[84],"activation":[85],"function.":[86],"Then":[87],"communication":[90],"graph":[91,97],"learned":[95],"neural":[98],"networks":[99],"based":[100],"on":[101,166],"new":[103],"mechanism.":[105],"Through":[106],"can":[112,152],"communicate":[113],"effective":[116],"as":[117,119],"well":[118],"efficient":[120],"way":[121],"via":[122],"only":[123],"selectively":[124],"attending":[125],"matter":[129],"most":[131],"scale":[135],"problem":[139],"reduced":[141],"little":[143],"optimality":[144],"compromised.":[145],"Comparative":[146],"results":[147],"show":[148],"our":[150],"algorithm":[151],"learn":[153],"interpretable":[155],"structure":[157],"outperforms":[159],"previous":[160],"significant":[164],"margin":[165],"applications":[167],"involving":[168],"system.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}