{"id":"https://openalex.org/W4207084068","doi":"https://doi.org/10.1109/gcwkshps52748.2021.9682129","title":"Understanding Exploration and Exploitation of Q-Learning Agents in B5G Network Management","display_name":"Understanding Exploration and Exploitation of Q-Learning Agents in B5G Network Management","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4207084068","doi":"https://doi.org/10.1109/gcwkshps52748.2021.9682129"},"language":"en","primary_location":{"id":"doi:10.1109/gcwkshps52748.2021.9682129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshps52748.2021.9682129","pdf_url":null,"source":{"id":"https://openalex.org/S4363605397","display_name":"2021 IEEE Globecom Workshops (GC Wkshps)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Globecom Workshops (GC Wkshps)","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/A5042426939","display_name":"Sayantini Majumdar","orcid":"https://orcid.org/0000-0001-5002-7349"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sayantini Majumdar","raw_affiliation_strings":["Munich Research Center, Huawei Technologies","Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Munich Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210129353"]},{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089631314","display_name":"Riccardo Trivisonno","orcid":"https://orcid.org/0000-0003-4190-5781"},"institutions":[{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Riccardo Trivisonno","raw_affiliation_strings":["Munich Research Center, Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Munich Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210129353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060144977","display_name":"Georg Carle","orcid":"https://orcid.org/0000-0002-2347-1839"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Carle","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042426939"],"corresponding_institution_ids":["https://openalex.org/I4210129353","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.08,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9313262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9886999726295471,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9886999726295471,"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/T12288","display_name":"Optimization and Search Problems","score":0.9758999943733215,"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/T13553","display_name":"Age of Information Optimization","score":0.973800003528595,"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/exploit","display_name":"Exploit","score":0.821035623550415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7791513800621033},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.608551561832428},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6000297665596008},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5818154811859131},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5634475946426392},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4464947283267975},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.44284379482269287},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4166656732559204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30087336897850037},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13583984971046448}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.821035623550415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791513800621033},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.608551561832428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6000297665596008},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5818154811859131},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5634475946426392},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4464947283267975},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.44284379482269287},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4166656732559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30087336897850037},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13583984971046448},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcwkshps52748.2021.9682129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshps52748.2021.9682129","pdf_url":null,"source":{"id":"https://openalex.org/S4363605397","display_name":"2021 IEEE Globecom Workshops (GC Wkshps)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2045522464","https://openalex.org/W2152835608","https://openalex.org/W2163613561","https://openalex.org/W2289733701","https://openalex.org/W2333874039","https://openalex.org/W2626820647","https://openalex.org/W2799030443","https://openalex.org/W2799899844","https://openalex.org/W3032998286","https://openalex.org/W3185469768","https://openalex.org/W6798868840"],"related_works":["https://openalex.org/W79913212","https://openalex.org/W2094884983","https://openalex.org/W2378898096","https://openalex.org/W560952460","https://openalex.org/W2290927522","https://openalex.org/W4283579741","https://openalex.org/W3066706303","https://openalex.org/W876159576","https://openalex.org/W2943612818","https://openalex.org/W4385152897"],"abstract_inverted_index":{"Auto-scaling":[0],"is":[1,112],"a":[2,69],"lifecycle":[3],"management":[4,125],"approach":[5],"that":[6,138,150],"automatically":[7],"scales":[8],"resources":[9],"(CPU,":[10],"memory":[11],"etc.)":[12],"based":[13,88],"on":[14,89,130,201],"incoming":[15],"load":[16],"to":[17,43,82,106,122,163,181,214,226],"optimize":[18],"resource":[19,64],"utilization.":[20],"Centralized":[21],"orchestration,":[22],"although":[23],"optimal,":[24],"comes":[25],"at":[26],"the":[27,48,61,90,95,101,133,151,155,188,193,202,206,212,217],"cost":[28],"of":[29,54,63,187,219,231],"high":[30],"signaling":[31],"overhead.":[32],"Alternatively,":[33],"decentralized":[34,233],"RL-based":[35],"approaches":[36],"such":[37,137],"as":[38],"Q-Learning":[39],"(QL)":[40],"are":[41],"envisaged":[42],"be":[44],"more":[45],"suitable":[46],"for":[47],"strict":[49],"latency":[50],"and":[51,198],"overhead":[52],"requirements":[53],"B5G/6G":[55,232],"use":[56],"cases,":[57],"while":[58],"also":[59],"minimizing":[60],"number":[62],"allocation":[65],"conflicts":[66],"encountered":[67],"in":[68,157,192],"distributed":[70],"setting.":[71],"Before":[72],"QL":[73,220],"agents":[74,117,139,156,180],"can":[75],"take":[76],"optimal":[77],"auto-scaling":[78],"decisions,":[79],"they":[80,92,99,103],"need":[81],"explore":[83,164],"or":[84,165],"evaluate":[85],"their":[86,108,158,175],"actions":[87],"feedback":[91],"receive":[93],"from":[94,174],"environment.":[96],"The":[97],"faster":[98],"learn,":[100],"sooner":[102],"could":[104],"begin":[105],"exploit":[107],"knowledge.":[109,144],"However,":[110],"it":[111],"not":[113],"clear":[114],"when":[115,132],"these":[116],"have":[118],"explored":[119],"long":[120],"enough":[121],"start":[123,141],"taking":[124],"actions.":[126],"This":[127,209],"paper":[128],"focuses":[129],"understanding":[131],"exploration":[134,189],"should":[135,160],"end":[136],"may":[140],"exploiting":[142],"built":[143],"In":[145],"our":[146],"approach,":[147],"we":[148,168],"posit":[149],"knowledge":[152],"accrued":[153],"by":[154],"Q-tables":[159],"indicate":[161],"whether":[162],"exploit.":[166],"Hence,":[167],"conceive":[169],"Knowledge":[170],"Indicators":[171],"(KIs)":[172],"derived":[173],"Q-tables.":[176],"These":[177],"KIs":[178],"enable":[179],"learn":[182],"autonomously,":[183],"thereby":[184,222],"enabling":[185],"adjustment":[186],"parameter":[190],"epsilon":[191],"epsilon-greedy":[194],"approach.":[195,208],"Convergence":[196],"results":[197],"corresponding":[199],"impact":[200],"system":[203],"performance":[204],"validate":[205],"proposed":[207],"work":[210],"has":[211],"potential":[213],"speed":[215],"up":[216],"convergence":[218],"agents,":[221],"providing":[223],"critical":[224],"hints":[225],"operators":[227],"targeting":[228],"live":[229],"deployments":[230],"network":[234],"management.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}