{"id":"https://openalex.org/W4407385492","doi":"https://doi.org/10.14778/3696435.3696441","title":"Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing","display_name":"Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4407385492","doi":"https://doi.org/10.14778/3696435.3696441"},"language":"en","primary_location":{"id":"doi:10.14778/3696435.3696441","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3696435.3696441","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5075787386","display_name":"Hanfei Yu","orcid":"https://orcid.org/0000-0001-5790-4981"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hanfei Yu","raw_affiliation_strings":["Stevens Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018750491","display_name":"Jacob Carter","orcid":"https://orcid.org/0000-0001-6875-1271"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Carter","raw_affiliation_strings":["Louisiana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446064","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9301-5989"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Stevens Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":"https://orcid.org/0000-0002-7253-2458"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Devesh Tiwari","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402612","display_name":"Jian Li","orcid":"https://orcid.org/0000-0003-3642-3569"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079637252","display_name":"Seung\u2010Jong Park","orcid":"https://orcid.org/0000-0001-7821-7793"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung-Jong Park","raw_affiliation_strings":["Missouri University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075787386"],"corresponding_institution_ids":["https://openalex.org/I108468826"],"apc_list":null,"apc_paid":null,"fwci":0.6294,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76664967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"18","issue":"1","first_page":"66","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/boosting","display_name":"Boosting (machine learning)","score":0.8067552447319031},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7547457218170166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5938622951507568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38870346546173096}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8067552447319031},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7547457218170166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5938622951507568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38870346546173096}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3696435.3696441","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3696435.3696441","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2918828872","https://openalex.org/W2962725887","https://openalex.org/W2982316857","https://openalex.org/W2987607480","https://openalex.org/W3209811848","https://openalex.org/W3210617645"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"demonstrated":[5],"significant":[6],"potential":[7],"in":[8],"various":[9],"applications,":[10],"including":[11],"gaming":[12],"AI,":[13],"robotics,":[14],"and":[15,22,35,44,114,133,168,200,202,208,213,232],"system":[16],"scheduling.":[17],"DRL":[18,42,92,128,156,198],"algorithms":[19,43,129,199],"produce,":[20],"sample,":[21],"learn":[23],"from":[24],"training":[25,51,78,87,124,157,226,234],"data":[26,149],"online":[27],"through":[28],"a":[29,122,180],"trial-and-error":[30],"process,":[31],"demanding":[32],"considerable":[33],"time":[34,82],"computational":[36],"resources.":[37,54],"To":[38,174],"address":[39],"this,":[40],"distributed":[41,91,127],"paradigms":[45],"have":[46],"been":[47],"developed":[48],"to":[49,63,101,107,154,185,230,238],"expedite":[50],"using":[52],"extensive":[53],"Through":[55],"carefully":[56],"designed":[57],"experiments,":[58],"we":[59,178],"are":[60,95],"the":[61,68,155,161,220],"first":[62],"observe":[64],"that":[65,130,217],"strategically":[66],"increasing":[67],"actor-environment":[69],"interactions":[70],"by":[71,141,166,228,236],"spawning":[72],"more":[73],"concurrent":[74,137],"actors":[75,138],"at":[76],"certain":[77],"rounds":[79],"within":[80],"ephemeral":[81],"frames":[83],"can":[84],"significantly":[85],"enhance":[86],"efficiency.":[88],"Yet,":[89],"current":[90],"solutions,":[93],"which":[94],"predominantly":[96],"server-based":[97],"(or":[98],"serverful),":[99],"fail":[100],"capitalize":[102],"on":[103,205],"these":[104],"opportunities":[105],"due":[106],"their":[108],"long":[109],"startup":[110],"times,":[111],"limited":[112],"adaptability,":[113],"cumbersome":[115],"scalability.":[116],"This":[117],"paper":[118],"proposes":[119],"Nitro":[120,147,159,187,195,218],",":[121,225],"generic":[123],"engine":[125],"for":[126,188],"enforces":[131],"timely":[132],"effective":[134],"boosting":[135,165,190],"with":[136,196,211],"instantaneously":[139],"spawned":[140],"serverless":[142,145],"computing.":[143],"With":[144],"functions,":[146],"adjusts":[148],"sampling":[150],"strategies":[151],"dynamically":[152],"according":[153],"demands.":[158],"seizes":[160],"opportunity":[162],"of":[163],"real-time":[164],"accurately":[167],"swiftly":[169],"detecting":[170],"an":[171],"empirical":[172],"metric.":[173],"achieve":[175],"cost":[176],"efficiency,":[177],"design":[179],"heuristic":[181],"actor":[182],"scaling":[183],"algorithm":[184],"guide":[186],"cost-aware":[189],"budget":[191],"allocation.":[192],"We":[193],"integrate":[194],"state-of-the-art":[197],"frameworks":[201],"evaluate":[203],"them":[204],"AWS":[206],"EC2":[207],"Lambda.":[209],"Experiments":[210],"Mujoco":[212],"Atari":[214],"benchmarks":[215],"show":[216],"improves":[219],"final":[221],"rewards":[222],"(":[223],"i.e.":[224],"quality)":[227],"up":[229,237],"6\u00d7":[231],"reduces":[233],"costs":[235],"42%.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}