{"id":"https://openalex.org/W3156362535","doi":"https://doi.org/10.1109/infocom42981.2021.9488863","title":"Leveraging Domain Knowledge for Robust Deep Reinforcement Learning in Networking","display_name":"Leveraging Domain Knowledge for Robust Deep Reinforcement Learning in Networking","publication_year":2021,"publication_date":"2021-05-10","ids":{"openalex":"https://openalex.org/W3156362535","doi":"https://doi.org/10.1109/infocom42981.2021.9488863","mag":"3156362535"},"language":"en","primary_location":{"id":"doi:10.1109/infocom42981.2021.9488863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom42981.2021.9488863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","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/A5101489016","display_name":"Ying Zheng","orcid":"https://orcid.org/0000-0001-8823-2460"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102918870","display_name":"Haoyu Chen","orcid":"https://orcid.org/0000-0002-4585-1680"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":["School of Information Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036041576","display_name":"Qingyang Duan","orcid":"https://orcid.org/0000-0002-9268-1979"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Duan","raw_affiliation_strings":["School of Information Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729354","display_name":"Lixiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixiang Lin","raw_affiliation_strings":["School of Information Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102254168","display_name":"Yiyang Shao","orcid":null},"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":"Yiyang Shao","raw_affiliation_strings":["Huawei Technologies Co. Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391924","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-2772-4856"},"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 Wang","raw_affiliation_strings":["Huawei Technologies Co. Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327844","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8639-3818"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063792608","display_name":"Yuedong Xu","orcid":"https://orcid.org/0000-0003-4168-3998"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuedong Xu","raw_affiliation_strings":["School of Information Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9779999852180481,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8351991772651672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872484922409058},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6825367212295532},{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.5600587725639343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169174671173096},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4653969705104828},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4318948984146118},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41606706380844116},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41561001539230347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40207934379577637},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34572458267211914}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8351991772651672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872484922409058},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6825367212295532},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.5600587725639343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169174671173096},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4653969705104828},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4318948984146118},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41606706380844116},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41561001539230347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40207934379577637},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34572458267211914},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom42981.2021.9488863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom42981.2021.9488863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W1982063824","https://openalex.org/W2022844530","https://openalex.org/W2121863487","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2167407752","https://openalex.org/W2201581102","https://openalex.org/W2250340166","https://openalex.org/W2540285146","https://openalex.org/W2546571074","https://openalex.org/W2736601468","https://openalex.org/W2744628735","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2768254111","https://openalex.org/W2802214001","https://openalex.org/W2859870583","https://openalex.org/W2883529420","https://openalex.org/W2946348792","https://openalex.org/W2951952563","https://openalex.org/W2953299687","https://openalex.org/W2963477884","https://openalex.org/W2963687836","https://openalex.org/W2964043796","https://openalex.org/W2968986602","https://openalex.org/W3044022314","https://openalex.org/W3047132563","https://openalex.org/W3047203996","https://openalex.org/W3048983622","https://openalex.org/W3100357905","https://openalex.org/W3138562521","https://openalex.org/W4298857966","https://openalex.org/W4300110528","https://openalex.org/W6600644339","https://openalex.org/W6637967152","https://openalex.org/W6638088447","https://openalex.org/W6683204974","https://openalex.org/W6687681856","https://openalex.org/W6691553443","https://openalex.org/W6692846177","https://openalex.org/W6732417791","https://openalex.org/W6741002519","https://openalex.org/W6753325967","https://openalex.org/W6762728350","https://openalex.org/W6792319309"],"related_works":["https://openalex.org/W2367468089","https://openalex.org/W2358591856","https://openalex.org/W4306904969","https://openalex.org/W2098133976","https://openalex.org/W2347416728","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W4315865067","https://openalex.org/W3208304128"],"abstract_inverted_index":{"The":[0,83,123],"past":[1],"few":[2],"years":[3],"has":[4,27],"witnessed":[5],"a":[6,70,146,237],"surge":[7],"of":[8,22,97,127,154,200,213,225,227],"interest":[9],"towards":[10],"deep":[11],"reinforcement":[12],"learning":[13,73,153],"(Deep":[14],"RL)":[15],"in":[16,37,175,241],"computer":[17],"networks.":[18],"With":[19],"extraordinary":[20],"ability":[21],"feature":[23],"extraction,":[24],"Deep":[25,92],"RL":[26],"the":[28,32,95,104,112,119,131,141,152,158,166,192,196,206,223,232],"potential":[29],"to":[30,80,110,150,163],"re-engineer":[31],"fundamental":[33],"resource":[34],"allocation":[35],"problems":[36],"networking":[38],"without":[39],"relying":[40],"on":[41],"pre-programmed":[42],"models":[43],"or":[44],"assumptions":[45],"about":[46],"dynamic":[47,242],"environments.":[48,243],"However,":[49],"such":[50],"black-box":[51],"systems":[52],"suffer":[53],"from":[54],"poor":[55,62],"robustness,":[56],"showing":[57],"high":[58],"performance":[59,197,212,240],"variance":[60],"and":[61,117,138,157,183,209,220,235],"tail":[63,211],"performance.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"propose":[69],"unified":[71],"Teacher-Student":[72,124,173],"framework":[74,174],"that":[75,191],"harnesses":[76],"rich":[77],"domain":[78],"knowledge":[79],"improve":[81],"robustness.":[82],"domain-specific":[84],"algorithms,":[85],"less":[86],"performant":[87],"but":[88],"more":[89,238],"trustable":[90],"than":[91],"RL,":[93],"play":[94],"role":[96],"teachers":[98],"providing":[99],"advice":[100,121],"at":[101,231],"critical":[102],"states;":[103],"student":[105,155],"neural":[106],"network":[107],"is":[108],"steered":[109],"maximize":[111],"expected":[113],"reward":[114,142],"as":[115],"usual":[116],"mimic":[118],"teacher's":[120],"meanwhile.":[122],"method":[125],"comprises":[126],"three":[128],"modules":[129],"where":[130],"confidence":[132],"check":[133],"module":[134,144,162],"locates":[135],"wrong":[136],"decisions":[137],"risky":[139],"decisions,":[140],"shaping":[143],"designs":[145],"new":[147],"updating":[148],"function":[149],"incentive":[151],"network,":[156],"prioritized":[159],"experience":[160],"replay":[161],"effectively":[164],"utilize":[165],"advised":[167],"actions.":[168],"We":[169],"further":[170],"implement":[171],"our":[172],"existing":[176],"video":[177],"streaming":[178],"(Pensieve),":[179],"load":[180],"balancing":[181],"(DeepLB)":[182],"TCP":[184],"congestion":[185],"control":[186],"(Aurora).":[187],"Experimental":[188],"results":[189],"manifest":[190],"proposed":[193],"approach":[194],"reduces":[195],"standard":[198],"deviation":[199],"DeepLB":[201],"by":[202,215,229],"37%;":[203],"it":[204,221],"improves":[205],"90th,":[207],"95th":[208],"99th":[210],"Pensieve":[214],"7.6%,":[216],"8.8%,":[217],"10.7%":[218],"respectively;":[219],"accelerates":[222],"rate":[224],"growth":[226],"Aurora":[228],"2x":[230],"initial":[233],"stage,":[234],"achieves":[236],"stable":[239]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}