{"id":"https://openalex.org/W4312038599","doi":"https://doi.org/10.1145/3528535.3565249","title":"Optimizing communication in deep reinforcement learning with <i>XingTian</i>","display_name":"Optimizing communication in deep reinforcement learning with <i>XingTian</i>","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4312038599","doi":"https://doi.org/10.1145/3528535.3565249"},"language":"en","primary_location":{"id":"doi:10.1145/3528535.3565249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3528535.3565249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IFIP International Middleware Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091272448","display_name":"Lichen Pan","orcid":"https://orcid.org/0000-0001-7451-0140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lichen Pan","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634624","display_name":"Jun Qian","orcid":"https://orcid.org/0000-0002-5823-3144"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Qian","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001914481","display_name":"Wei Xia","orcid":"https://orcid.org/0000-0002-1099-4294"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076505011","display_name":"Hangyu Mao","orcid":"https://orcid.org/0000-0002-4499-7581"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangyu Mao","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382929","display_name":"Jun Yao","orcid":"https://orcid.org/0000-0003-2682-8650"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yao","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001255720","display_name":"Pengze Li","orcid":"https://orcid.org/0000-0001-7015-0491"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengze Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979232","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0002-6784-9709"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/computer-science","display_name":"Computer science","score":0.8242499828338623},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7743688225746155},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7349407076835632},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6824526190757751},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6814591288566589},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5012717247009277},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33314573764801025},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.31756430864334106},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.31321316957473755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2645585536956787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22399380803108215},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12596046924591064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242499828338623},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7743688225746155},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7349407076835632},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6824526190757751},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6814591288566589},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5012717247009277},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33314573764801025},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.31756430864334106},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.31321316957473755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2645585536956787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22399380803108215},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12596046924591064}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3528535.3565249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3528535.3565249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IFIP International Middleware Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2076337359","https://openalex.org/W2098432798","https://openalex.org/W2602856279","https://openalex.org/W2607662938","https://openalex.org/W2766447205","https://openalex.org/W2902907165","https://openalex.org/W2914209329","https://openalex.org/W2963821308","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W2997070234","https://openalex.org/W2998489261","https://openalex.org/W3118210634","https://openalex.org/W3139377883","https://openalex.org/W3183892796","https://openalex.org/W3206040568","https://openalex.org/W4285604331","https://openalex.org/W6603593944","https://openalex.org/W6669402789"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2042919702","https://openalex.org/W2150611273","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4207086172","https://openalex.org/W4380318855","https://openalex.org/W2109294620"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"achieves":[4,189],"great":[5],"success":[6],"in":[7,11,68,90,97,100,199],"various":[8],"domains.":[9],"Communication":[10],"today's":[12],"DRL":[13,24,57,70,80,91,98,127,152,155,187],"algorithms":[14,99,156],"takes":[15,119],"non-negligible":[16],"time":[17,64],"compared":[18],"to":[19,35,40,162],"the":[20,42,45,50,53,66,84,95,112,122,150,185,194],"computation.":[21],"However,":[22],"prior":[23,69],"frameworks":[25],"usually":[26],"focus":[27],"on":[28,158],"computation":[29,67,89,96],"management":[30,85],"while":[31],"paying":[32],"little":[33],"attention":[34],"communication":[36,51,60,87,108,113,178],"optimization,":[37],"and":[38,88,104,116,118,138,184,205],"fail":[39],"utilize":[41],"opportunity":[43,125],"of":[44,56,86,121],"communication-computation":[46,123],"overlap":[47],"that":[48,82,132],"hides":[49],"from":[52,126],"critical":[54],"path":[55],"algorithms.":[58,92,128],"Consequently,":[59],"can":[61,139],"take":[62],"more":[63,164],"than":[65,166,193],"frameworks.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"present":[76],"XingTian,":[77],"a":[78,101],"novel":[79],"framework":[81,153],"co-designs":[83],"XingTian":[93,110,133,159,175,202],"organizes":[94],"decentralized":[102],"way":[103],"provides":[105],"an":[106],"asynchronous":[107],"channel.":[109],"makes":[111],"execute":[114],"asynchronously":[115],"aggressively":[117],"advantage":[120],"overlapping":[124],"Experimental":[129],"results":[130],"show":[131],"improves":[134],"data":[135,146],"transmission":[136],"efficiency":[137,179],"transmit":[140],"at":[141,208],"least":[142],"twice":[143],"as":[144,149],"much":[145],"per":[147],"second":[148],"state-of-the-art":[151],"RLLib.":[154],"based":[157],"achieve":[160],"up":[161],"70.71%":[163],"throughput":[165,192],"RLLib-based":[167,195],"ones":[168],"with":[169],"better":[170],"or":[171],"similar":[172],"convergent":[173],"performance.":[174],"maintains":[176],"high":[177],"under":[180],"different":[181],"scale":[182],"deployments":[183],"XingTian-based":[186],"algorithm":[188],"91.12%":[190],"higher":[191],"one":[196],"when":[197],"deployed":[198],"four":[200],"machines.":[201],"is":[203],"open-sourced":[204],"publicly":[206],"available":[207],"https://github.com/huawei-noah/xingtian.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}