{"id":"https://openalex.org/W3116026360","doi":"https://doi.org/10.1109/hpec43674.2020.9286212","title":"Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research","display_name":"Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3116026360","doi":"https://doi.org/10.1109/hpec43674.2020.9286212","mag":"3116026360"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5069248471","display_name":"Yutai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yutai Zhou","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, US"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, US","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016926782","display_name":"Shawn Manuel","orcid":"https://orcid.org/0009-0003-6462-6512"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shawn Manuel","raw_affiliation_strings":["Stanford University, Stanford, CA, US"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, US","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062745383","display_name":"Peter Morales","orcid":"https://orcid.org/0000-0003-4924-0892"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Morales","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, US"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, US","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Stanford University, Stanford, CA, US"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, US","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055398987","display_name":"Jaime Pe\u00f1a","orcid":"https://orcid.org/0009-0008-6472-5605"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Pena","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, US"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, US","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005883173","display_name":"Ross Allen","orcid":"https://orcid.org/0000-0003-3730-641X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Allen","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, US"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, US","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069248471"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17861144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1902 7151","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9965000152587891,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9843999743461609,"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":0.9172691106796265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782441258430481},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5940232872962952},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5898669958114624},{"id":"https://openalex.org/keywords/football","display_name":"Football","score":0.5393677949905396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848862588405609},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4771013855934143},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.4362056851387024},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42849379777908325},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40440797805786133},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36999306082725525},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3338320851325989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9172691106796265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782441258430481},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5940232872962952},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5898669958114624},{"id":"https://openalex.org/C2778444522","wikidata":"https://www.wikidata.org/wiki/Q1081491","display_name":"Football","level":2,"score":0.5393677949905396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848862588405609},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4771013855934143},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4362056851387024},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42849379777908325},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40440797805786133},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36999306082725525},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3338320851325989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W13821285","https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1508143344","https://openalex.org/W1512866498","https://openalex.org/W1596936080","https://openalex.org/W1771410628","https://openalex.org/W1908253641","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2121943493","https://openalex.org/W2134281179","https://openalex.org/W2134779831","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2175259684","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2402144811","https://openalex.org/W2545546008","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2754517384","https://openalex.org/W2757564505","https://openalex.org/W2768629321","https://openalex.org/W2781585732","https://openalex.org/W2809256243","https://openalex.org/W2811374584","https://openalex.org/W2883672905","https://openalex.org/W2889987506","https://openalex.org/W2891663723","https://openalex.org/W2897851150","https://openalex.org/W2898436992","https://openalex.org/W2898621204","https://openalex.org/W2902907165","https://openalex.org/W2905342215","https://openalex.org/W2911616846","https://openalex.org/W2913662073","https://openalex.org/W2941355526","https://openalex.org/W2952095743","https://openalex.org/W2953384591","https://openalex.org/W2962938168","https://openalex.org/W2963094322","https://openalex.org/W2963243556","https://openalex.org/W2963390429","https://openalex.org/W2963864421","https://openalex.org/W2963881016","https://openalex.org/W2964014087","https://openalex.org/W2964043796","https://openalex.org/W2970971581","https://openalex.org/W2972093249","https://openalex.org/W2975835314","https://openalex.org/W2977083973","https://openalex.org/W2982316857","https://openalex.org/W2994073215","https://openalex.org/W2996037775","https://openalex.org/W2997326755","https://openalex.org/W2997502221","https://openalex.org/W3011672202","https://openalex.org/W3032773894","https://openalex.org/W3036295212","https://openalex.org/W3106525532","https://openalex.org/W3148740559","https://openalex.org/W4288076474","https://openalex.org/W4288118072","https://openalex.org/W4288594419","https://openalex.org/W4289100326","https://openalex.org/W4295312788","https://openalex.org/W4295830359","https://openalex.org/W4296611641","https://openalex.org/W4299802797","https://openalex.org/W6630802251","https://openalex.org/W6638018090","https://openalex.org/W6640044251","https://openalex.org/W6678204714","https://openalex.org/W6680096503","https://openalex.org/W6692846177","https://openalex.org/W6713134421","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6747481501","https://openalex.org/W6752603789","https://openalex.org/W6752963931","https://openalex.org/W6754964036","https://openalex.org/W6755489178","https://openalex.org/W6757784512","https://openalex.org/W6757988111","https://openalex.org/W6758846586","https://openalex.org/W6766978945","https://openalex.org/W6780559895","https://openalex.org/W6788151078"],"related_works":["https://openalex.org/W2347401120","https://openalex.org/W2041961361","https://openalex.org/W2310010941","https://openalex.org/W1988132375","https://openalex.org/W2334292868","https://openalex.org/W579144800","https://openalex.org/W2147233680","https://openalex.org/W2069525434","https://openalex.org/W2046798653","https://openalex.org/W2021057137"],"abstract_inverted_index":{"Some":[0],"of":[1,23,32,52,82,100,115],"the":[2,11,50,75,98,112,116,127],"most":[3],"important":[4],"publications":[5],"in":[6,35],"deep":[7],"reinforcement":[8,101],"learning":[9,84,102],"over":[10],"last":[12],"few":[13],"years":[14],"have":[15],"been":[16],"fueled":[17],"by":[18,135],"access":[19],"to":[20],"massive":[21],"amounts":[22],"computation":[24,56],"through":[25],"large":[26],"scale":[27],"distributed":[28,64],"systems.":[29],"The":[30],"success":[31],"these":[33,53,108,119,141],"approaches":[34,54],"achieving":[36],"human-expert":[37],"level":[38],"performance":[39],"on":[40,107,118,140],"several":[41],"complex":[42],"video-game":[43],"environments":[44,109],"has":[45],"motivated":[46],"further":[47],"exploration":[48],"into":[49],"limits":[51],"as":[55,74,86],"increases.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,122],"present":[62],"a":[63,80],"RL":[65,133],"training":[66],"framework":[67],"designed":[68],"for":[69,131],"super":[70],"computing":[71],"infrastructures":[72],"such":[73],"MIT":[76],"SuperCloud.":[77],"We":[78,104],"review":[79],"collection":[81],"challenging":[83],"environments-such":[85],"Google":[87],"Research":[88],"Football,":[89],"StarCraft":[90],"II,":[91],"and":[92,125],"Multi-Agent":[93],"Mujoco-":[94],"which":[95],"are":[96],"at":[97],"frontier":[99],"research.":[103],"provide":[105],"results":[106],"that":[110],"illustrate":[111],"current":[113],"state":[114],"field":[117],"problems.":[120],"Finally,":[121],"also":[123],"quantify":[124],"discuss":[126],"computational":[128],"requirements":[129],"needed":[130],"performing":[132],"research":[134],"enumerating":[136],"all":[137],"experiments":[138],"performed":[139],"environments.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}