{"id":"https://openalex.org/W4302012809","doi":"https://doi.org/10.48550/arxiv.2210.00882","title":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","display_name":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","publication_year":2022,"publication_date":"2022-10-03","ids":{"openalex":"https://openalex.org/W4302012809","doi":"https://doi.org/10.48550/arxiv.2210.00882"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.00882","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.00882","pdf_url":"https://arxiv.org/pdf/2210.00882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.00882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072678098","display_name":"Huanzhou Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhu, Huanzhou","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025795919","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-0768-3444","observed_orcids":["https://orcid.org/0000-0002-0768-3444","https://orcid.org/0009-0005-1328-3622"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao, Bo","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389298","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-9597-497X","observed_orcids":["https://orcid.org/0000-0002-9597-497X","https://orcid.org/0000-0002-7483-0045"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Gang","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749973","display_name":"Weifeng Chen","orcid":"https://orcid.org/0000-0002-5850-0759","observed_orcids":["https://orcid.org/0000-0002-5850-0759"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen, Weifeng","raw_affiliation_strings":["Huawei Technologies Co., Ltd","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982344","display_name":"Yijie Chen","orcid":"https://orcid.org/0000-0003-4791-9762","observed_orcids":["https://orcid.org/0000-0003-4791-9762"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen, Yijie","raw_affiliation_strings":["Huawei Technologies Co., Ltd","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783247","display_name":"Liang Shi","orcid":"https://orcid.org/0000-0002-2397-0291","observed_orcids":["https://orcid.org/0000-0002-2397-0291"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Liang","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613","observed_orcids":["https://orcid.org/0000-0001-8132-5613","https://orcid.org/0000-0001-8660-2376"]},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang, Yaodong","raw_affiliation_strings":["Huawei R&D United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei R&D United Kingdom","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078842469","display_name":"Peter R. Pietzuch","orcid":"https://orcid.org/0000-0002-6963-5640","observed_orcids":["https://orcid.org/0000-0002-6963-5640"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pietzuch, Peter","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806","observed_orcids":["https://orcid.org/0000-0002-8257-5806","https://orcid.org/0000-0002-1054-5501","https://orcid.org/0000-0002-4912-3293","https://orcid.org/0000-0002-7918-8936","https://orcid.org/0000-0003-4664-0700"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Lei","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.49410000443458557,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.49410000443458557,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.48339998722076416,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/distributed-reinforcement-learning","display_name":"distributed reinforcement learning","score":0.9950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765202760696411},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8237168788909912},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6899959444999695},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6438503265380859},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5628676414489746},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5531491041183472},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5363888144493103},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5209221243858337},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45752155780792236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27192842960357666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15692803263664246}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:2210.00882","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.00882","pdf_url":"https://arxiv.org/pdf/2210.00882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-131910","doi":null,"is_oa":true,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2023&rft.spage=977&rft.aulast=Zhu&rft.aufirst=Huan&rft.atitle=MSRL%3A+Distributed+Reinforcement+Learning+with+Dataflow+Fragments&rft.title=PROCEEDINGS+OF+THE+2023+USENIX+ANNUAL+TECHNICAL+CONFERENCE","pdf_url":"https://www.usenix.org/system/files/atc23-zhu-huanzhou.pdf","source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123833","doi":null,"is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/c91f6be1-b14f-47e9-8f12-fb77570025e7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/107727","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/107727","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"USENIX Annual Technical Conference (USENIX ATC)","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.2210.00882","doi":"https://doi.org/10.48550/arxiv.2210.00882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.00882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.00882","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.00882","pdf_url":"https://arxiv.org/pdf/2210.00882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W4214505573"],"abstract_inverted_index":{"Reinforcement":[0,79],"learning":[1,155],"(RL)":[2],"trains":[3],"many":[4],"agents,":[5],"which":[6,121],"is":[7,97],"resource-intensive":[8],"and":[9,25,49,99],"must":[10],"scale":[11],"to":[12,40,107,131,144,178],"large":[13],"GPU":[14,62],"clusters.":[15],"Different":[16],"RL":[17,32,38,71,84,94,127,176],"training":[18,85,95,129,177],"algorithms":[19,39,72],"offer":[20],"different":[21,139],"opportunities":[22],"for":[23],"distributing":[24],"parallelising":[26],"the":[27,35,55,108,113,168],"computation.":[28],"Yet,":[29],"current":[30,65],"distributed":[31,42,83,100],"systems":[33,66],"tie":[34],"definition":[36],"of":[37,54,116,171],"their":[41,74],"execution:":[43],"they":[44],"hard-code":[45],"particular":[46],"distribution":[47,89,169],"strategies":[48,170],"only":[50],"accelerate":[51],"specific":[52],"parts":[53],"computation":[56,96],"(e.g.":[57],"policy":[58],"network":[59],"updates)":[60],"on":[61,101,138],"workers.":[63],"Fundamentally,":[64],"lack":[67],"abstractions":[68],"that":[69,87,91,165],"decouple":[70],"from":[73,125],"execution.":[75],"We":[76,163],"describe":[77],"MindSpore":[78],"Learning":[80],"(MSRL),":[81],"a":[82,117],"system":[86],"supports":[88],"policies":[90],"govern":[92],"how":[93],"parallelised":[98],"cluster":[102],"resources,":[103],"without":[104],"requiring":[105],"changes":[106],"algorithm":[109],"implementation.":[110],"MSRL":[111,166],"introduces":[112],"new":[114],"abstraction":[115],"fragmented":[118],"dataflow":[119,146],"graph,":[120],"maps":[122],"Python":[123],"functions":[124],"an":[126],"algorithm's":[128],"loop":[130],"parallel":[132],"computational":[133,149],"fragments.":[134],"Fragments":[135],"are":[136],"executed":[137],"devices":[140],"by":[141,153],"translating":[142],"them":[143],"low-level":[145],"representations,":[147],"e.g.":[148],"graphs":[150],"as":[151],"supported":[152],"deep":[154],"engines,":[156],"CUDA":[157],"implementations":[158],"or":[159],"multi-threaded":[160],"CPU":[161],"processes.":[162],"show":[164],"subsumes":[167],"existing":[172],"systems,":[173],"while":[174],"scaling":[175],"64":[179],"GPUs.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}