{"id":"https://openalex.org/W4381734243","doi":"https://doi.org/10.1109/noms56928.2023.10154210","title":"MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks","display_name":"MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks","publication_year":2023,"publication_date":"2023-05-08","ids":{"openalex":"https://openalex.org/W4381734243","doi":"https://doi.org/10.1109/noms56928.2023.10154210"},"language":"en","primary_location":{"id":"doi:10.1109/noms56928.2023.10154210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms56928.2023.10154210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium","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":"https://openalex.org/A5059453270","display_name":"Raffaele Galliera","orcid":null},"institutions":[{"id":"https://openalex.org/I1335578998","display_name":"Florida Institute for Human and Machine Cognition","ror":"https://ror.org/02napvw46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335578998"]},{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raffaele Galliera","raw_affiliation_strings":["Florida Institute for Human & Machine Cognition (IHMC)","Department of Intelligent Systems & Robotics, The University of West Florida (UWF), Pensacola, FL, USA"],"affiliations":[{"raw_affiliation_string":"Florida Institute for Human & Machine Cognition (IHMC)","institution_ids":["https://openalex.org/I1335578998"]},{"raw_affiliation_string":"Department of Intelligent Systems & Robotics, The University of West Florida (UWF), Pensacola, FL, USA","institution_ids":["https://openalex.org/I83683471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065552686","display_name":"Alessandro Morelli","orcid":"https://orcid.org/0000-0003-3309-3461"},"institutions":[{"id":"https://openalex.org/I1335578998","display_name":"Florida Institute for Human and Machine Cognition","ror":"https://ror.org/02napvw46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335578998"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Morelli","raw_affiliation_strings":["Florida Institute for Human & Machine Cognition (IHMC)"],"affiliations":[{"raw_affiliation_string":"Florida Institute for Human & Machine Cognition (IHMC)","institution_ids":["https://openalex.org/I1335578998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063993549","display_name":"Roberto Fronteddu","orcid":null},"institutions":[{"id":"https://openalex.org/I1335578998","display_name":"Florida Institute for Human and Machine Cognition","ror":"https://ror.org/02napvw46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335578998"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Fronteddu","raw_affiliation_strings":["Florida Institute for Human & Machine Cognition (IHMC)"],"affiliations":[{"raw_affiliation_string":"Florida Institute for Human & Machine Cognition (IHMC)","institution_ids":["https://openalex.org/I1335578998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047412092","display_name":"Niranjan Suri","orcid":"https://orcid.org/0000-0003-2982-8218"},"institutions":[{"id":"https://openalex.org/I1335578998","display_name":"Florida Institute for Human and Machine Cognition","ror":"https://ror.org/02napvw46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1335578998"]},{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]},{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niranjan Suri","raw_affiliation_strings":["Florida Institute for Human & Machine Cognition (IHMC)","Department of Intelligent Systems & Robotics, The University of West Florida (UWF), Pensacola, FL, USA","US Army Research Laboratory (ARL), Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"Florida Institute for Human & Machine Cognition (IHMC)","institution_ids":["https://openalex.org/I1335578998"]},{"raw_affiliation_string":"Department of Intelligent Systems & Robotics, The University of West Florida (UWF), Pensacola, FL, USA","institution_ids":["https://openalex.org/I83683471"]},{"raw_affiliation_string":"US Army Research Laboratory (ARL), Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059453270"],"corresponding_institution_ids":["https://openalex.org/I1335578998","https://openalex.org/I83683471"],"apc_list":null,"apc_paid":null,"fwci":1.2055,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79623137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10138","display_name":"Network Traffic and Congestion Control","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9995999932289124,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9973000288009644,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9969000220298767,"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":0.8248112201690674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6528749465942383},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49082979559898376},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.4253905415534973},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4244089722633362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3465206027030945},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32283926010131836}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8248112201690674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6528749465942383},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49082979559898376},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.4253905415534973},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4244089722633362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465206027030945},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32283926010131836},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/noms56928.2023.10154210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms56928.2023.10154210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium","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":50,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1583837637","https://openalex.org/W1792364413","https://openalex.org/W2022844530","https://openalex.org/W2107527140","https://openalex.org/W2112495447","https://openalex.org/W2116527688","https://openalex.org/W2137166796","https://openalex.org/W2139378549","https://openalex.org/W2159407003","https://openalex.org/W2540285146","https://openalex.org/W2734941459","https://openalex.org/W2745739520","https://openalex.org/W2781726626","https://openalex.org/W2885163910","https://openalex.org/W2904246096","https://openalex.org/W2913954081","https://openalex.org/W2914189542","https://openalex.org/W2920933065","https://openalex.org/W2944459545","https://openalex.org/W2954711779","https://openalex.org/W2979501713","https://openalex.org/W3011174400","https://openalex.org/W3016712945","https://openalex.org/W3091574512","https://openalex.org/W3127399923","https://openalex.org/W3144454280","https://openalex.org/W3174203314","https://openalex.org/W3185226120","https://openalex.org/W3203951668","https://openalex.org/W3216772467","https://openalex.org/W4213251304","https://openalex.org/W4286571609","https://openalex.org/W4286963241","https://openalex.org/W4296906395","https://openalex.org/W4297797010","https://openalex.org/W4298230560","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6684260611","https://openalex.org/W6742876389","https://openalex.org/W6746684068","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6753859785","https://openalex.org/W6762728350","https://openalex.org/W6765213128","https://openalex.org/W6766978945","https://openalex.org/W6769138899","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Fast":[0],"and":[1,25,34,101,103,148],"efficient":[2],"transport":[3],"protocols":[4],"are":[5],"the":[6,29,39,93,105,126,143,200],"foundation":[7],"of":[8,15,32,41,54,67,145],"an":[9,71,109],"increasingly":[10],"distributed":[11],"world.":[12],"The":[13,52],"burden":[14],"continuously":[16],"delivering":[17],"improved":[18],"communication":[19],"performance":[20],"to":[21,63,81,97,124,136,151,168],"support":[22],"next-generation":[23],"applications":[24],"services,":[26],"combined":[27],"with":[28,119,170],"increasing":[30],"heterogeneity":[31],"systems":[33],"network":[35,118],"technologies,":[36],"has":[37],"promoted":[38],"design":[40],"Congestion":[42],"Control":[43],"(CC)":[44],"algorithms":[45,197],"that":[46,60,129,162,186],"perform":[47],"well":[48],"under":[49],"specific":[50],"environments.":[51],"challenge":[53],"designing":[55],"a":[56,64,83,116,175,190],"generic":[57],"CC":[58,196],"algorithm":[59,96],"can":[61,164],"adapt":[62],"broad":[65],"range":[66],"scenarios":[68],"is":[69,157],"still":[70],"open":[72],"research":[73,156],"question.":[74],"To":[75],"tackle":[76],"this":[77],"challenge,":[78],"we":[79,184],"propose":[80],"apply":[82],"novel":[84],"Reinforcement":[85],"Learning":[86],"(RL)":[87],"approach.":[88],"Our":[89],"solution,":[90],"MARLIN,":[91],"uses":[92],"Soft":[94],"Actor-Critic":[95],"maximize":[98],"both":[99],"entropy":[100,202],"return":[102],"models":[104],"learning":[106],"process":[107],"as":[108],"infinite-horizon":[110],"task.":[111],"We":[112,138],"trained":[113],"MARLIN":[114,163],"on":[115,142,199],"real":[117],"varying":[120],"background":[121],"traffic":[122],"patterns":[123],"overcome":[125],"sim-to-real":[127],"mismatch":[128],"researchers":[130],"have":[131,160],"encountered":[132],"when":[133],"applying":[134],"RL":[135,203],"CC.":[137],"evaluated":[139],"our":[140,187],"solution":[141],"task":[144,176],"file":[146],"transfer":[147],"compared":[149],"it":[150],"TCP":[152,169],"Cubic.":[153],"While":[154],"further":[155],"required,":[158],"results":[159,167],"shown":[161],"achieve":[165],"comparable":[166],"little":[171],"hyperparameter":[172],"tuning,":[173],"in":[174],"significantly":[177],"different":[178],"from":[179],"its":[180],"training":[181],"setting.":[182],"Therefore,":[183],"believe":[185],"work":[188],"represents":[189],"promising":[191],"first":[192],"step":[193],"towards":[194],"building":[195],"based":[198],"maximum":[201],"framework.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-06-24T00:00:00"}