{"id":"https://openalex.org/W3117513924","doi":"https://doi.org/10.1109/ictc49870.2020.9289179","title":"Train Throughput Analysis of Distributed Reinforcement Learning","display_name":"Train Throughput Analysis of Distributed Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3117513924","doi":"https://doi.org/10.1109/ictc49870.2020.9289179","mag":"3117513924"},"language":"en","primary_location":{"id":"doi:10.1109/ictc49870.2020.9289179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5070677616","display_name":"Sooyoung Jang","orcid":"https://orcid.org/0000-0002-6931-9592"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sooyoung Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027995571","display_name":"Noh-Sam Park","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Noh-Sam Park","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070677616"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18189525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1189","last_page":"1192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9714000225067139,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/throughput","display_name":"Throughput","score":0.8592286109924316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8233654499053955},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8160676956176758},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7978307604789734},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6793054342269897},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5855761170387268},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.584642231464386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3113328218460083},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.13331854343414307},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.100534588098526},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0918084979057312}],"concepts":[{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.8592286109924316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8233654499053955},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8160676956176758},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7978307604789734},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6793054342269897},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5855761170387268},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.584642231464386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3113328218460083},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.13331854343414307},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.100534588098526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0918084979057312},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc49870.2020.9289179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2811374584","https://openalex.org/W2963094322","https://openalex.org/W2963390429","https://openalex.org/W2963985863","https://openalex.org/W3032773894","https://openalex.org/W4295830359","https://openalex.org/W4296611641","https://openalex.org/W4297797010","https://openalex.org/W6747481501","https://openalex.org/W6748638692","https://openalex.org/W6752963931","https://openalex.org/W6779380009","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2135248929","https://openalex.org/W2092690310","https://openalex.org/W2011430815","https://openalex.org/W1493624592","https://openalex.org/W3190662310","https://openalex.org/W4321606653","https://openalex.org/W1507878993","https://openalex.org/W2798440551"],"abstract_inverted_index":{"Distributed":[0],"deep":[1],"reinforcement":[2,76],"learning":[3,44,77,89],"can":[4,192],"increase":[5],"the":[6,13,42,47,51,53,58,62,67,75,79,87,93,105,145,151,158,167,170,175,181,186,189,198,208],"train":[7,106,140,152,171,199],"throughput,":[8],"which":[9,29],"is":[10,71,109,163,185],"defined":[11],"as":[12,197],"timesteps":[14],"per":[15],"second":[16],"used":[17],"for":[18,35],"training,":[19],"easily":[20],"by":[21,206],"just":[22],"adding":[23],"computing":[24,55,64,183],"nodes":[25],"to":[26,157,165,203,212],"a":[27,120,125,194],"cluster,":[28],"makes":[30],"it":[31,162],"an":[32],"essential":[33],"technique":[34],"solving":[36],"complex":[37,127],"problems.":[38],"The":[39,129],"more":[40,52],"complicated":[41],"virtual":[43,88],"environment":[45,90],"and":[46,61,91,113,123,136,173,178],"policy":[48,68,94],"network":[49],"become,":[50],"CPU":[54],"power":[56,65,184],"in":[57,66,86,169],"rollout":[59,85],"phase":[60,70],"GPU":[63,182],"update":[69],"required.":[72],"Recall":[73],"that":[74,96,149],"iterates":[78],"phases":[80],"of":[81,100,131],"acquiring":[82],"data":[83,97],"through":[84],"updating":[92],"from":[95,210],"over":[98],"millions":[99],"iterations.":[101],"In":[102],"this":[103],"paper,":[104],"throughput":[107,141,153,172,200],"analysis":[108],"performed":[110],"with":[111],"RLlib":[112],"IMPALA":[114],"on":[115,139],"two":[116],"different":[117],"problems:":[118],"CartPole,":[119],"simple":[121],"problem,":[122],"Pong,":[124],"relatively":[126],"problem.":[128],"effects":[130],"various":[132],"scalability":[133,159],"metrics,":[134,160],"clustering,":[135],"observation":[137,190],"dimensions":[138,191],"are":[142],"analyzed.":[143],"Throughout":[144],"analysis,":[146],"we":[147],"show":[148],"1)":[150],"varies":[154],"significantly":[155],"according":[156],"2)":[161],"vital":[164],"monitor":[166],"bottleneck":[168],"configure":[174],"cluster":[176],"accordingly,":[177],"3)":[179],"when":[180],"bottleneck,":[187],"reducing":[188,207],"be":[193],"great":[195],"option":[196],"increases":[201],"up":[202],"3":[204],"times":[205],"dimension":[209],"84":[211],"42.":[213]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}