{"id":"https://openalex.org/W7084090313","doi":"https://doi.org/10.1109/infocom55648.2025.11044699","title":"Multi-Task Reinforcement Learning for Collaborative Network Optimization in Data Centers","display_name":"Multi-Task Reinforcement Learning for Collaborative Network Optimization in Data Centers","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W7084090313","doi":"https://doi.org/10.1109/infocom55648.2025.11044699"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","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":null,"display_name":"Ting Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Wang","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Cheng","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiao Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Du","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50669794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.5719000101089478,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.5719000101089478,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.1420000046491623,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10593","display_name":"Bacterial biofilms and quorum sensing","score":0.03669999912381172,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7343000173568726},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5949000120162964},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5235000252723694},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.4343999922275543},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.3637999892234802},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.358599990606308},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.3513000011444092},{"id":"https://openalex.org/keywords/active-queue-management","display_name":"Active queue management","score":0.3296999931335449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014000058174133},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7343000173568726},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5949000120162964},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.4343999922275543},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C34793927","wikidata":"https://www.wikidata.org/wiki/Q583367","display_name":"Active queue management","level":4,"score":0.3296999931335449},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2779888511","wikidata":"https://www.wikidata.org/wiki/Q244156","display_name":"Traffic congestion","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5227875867","display_name":null,"funder_award_id":"62441605","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"data":[1],"center":[2],"networks":[3],"increasingly":[4],"grow":[5],"in":[6,41,189],"complexity":[7],"and":[8,14,39,46,75,80,95,165,194],"scale,":[9],"efficiently":[10],"managing":[11],"traffic":[12,93,148],"scheduling":[13,94],"congestion":[15,96,124],"control":[16,97],"becomes":[17],"crucial":[18],"for":[19,109,123,146],"optimizing":[20],"network":[21,101,198],"performance.":[22],"Traditional":[23],"single-task":[24],"optimization":[25,107],"strategies":[26],"often":[27],"fall":[28],"short,":[29],"failing":[30],"to":[31,104,118,129,161,174],"adequately":[32],"address":[33],"the":[34,127],"interplay":[35],"between":[36],"different":[37],"tasks":[38],"resulting":[40],"suboptimal":[42],"performance":[43],"with":[44,73,126],"inefficiencies":[45],"robustness":[47,195],"issues.":[48,132],"To":[49],"tackle":[50],"these":[51],"challenges,":[52],"this":[53],"paper":[54],"proposes":[55],"a":[56,70,153,166],"novel":[57],"Multi-Task":[58],"Reinforcement":[59],"Learning":[60],"(MTRL)-based":[61],"collaborative":[62],"Network":[63],"Optimization":[64],"scheme,":[65],"termed":[66],"MTRLNO,":[67],"which":[68],"establishes":[69],"structured":[71],"framework":[72],"central":[74,84],"edge":[76,110],"systems":[77],"(i.e.,":[78],"hosts":[79],"switches).":[81],"The":[82],"SDN-enabled":[83],"system":[85],"incorporates":[86],"an":[87,135],"MTRL":[88],"agent":[89],"that":[90,183],"simultaneously":[91],"optimizes":[92],"tasks,":[98],"leveraging":[99],"global":[100],"state":[102],"information":[103],"formulate":[105],"instructive":[106],"policies":[108],"systems.":[111],"Switches":[112],"implement":[113],"decentralized":[114],"multi-agent":[115],"RL":[116],"agents":[117],"facilitate":[119],"automatic":[120],"ECN":[121],"tuning":[122],"control,":[125],"ability":[128],"handle":[130],"incast":[131],"Hosts":[133],"feature":[134],"MTRL-guided":[136],"Multiple":[137],"Level":[138],"Feedback":[139],"Queue":[140],"(MLFQ)":[141],"demotion":[142],"threshold":[143],"adjustment":[144],"scheme":[145],"adaptive":[147],"scheduling.":[149],"We":[150],"further":[151],"develop":[152],"Prioritized":[154],"Experience":[155],"Replay-based":[156],"Soft":[157],"Actor-Critic":[158],"(PERSAC)":[159],"algorithm":[160,170],"enhance":[162],"learning":[163,169],"efficiency":[164],"customized":[167],"multi-task":[168],"via":[171],"improved":[172],"parameter-sharing":[173],"effectively":[175],"adapt":[176],"across":[177,196],"multiple":[178],"tasks.":[179],"Experimental":[180],"results":[181],"demonstrate":[182],"MTRLNO":[184],"significantly":[185],"outperforms":[186],"state-of-the-art":[187],"approaches":[188],"terms":[190],"of":[191],"FCT,":[192],"latency,":[193],"diverse":[197],"conditions.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
