{"id":"https://openalex.org/W4213324132","doi":"https://doi.org/10.3390/s22041651","title":"Multi-Agent Reinforcement Learning for Joint Cooperative Spectrum Sensing and Channel Access in Cognitive UAV Networks","display_name":"Multi-Agent Reinforcement Learning for Joint Cooperative Spectrum Sensing and Channel Access in Cognitive UAV Networks","publication_year":2022,"publication_date":"2022-02-20","ids":{"openalex":"https://openalex.org/W4213324132","doi":"https://doi.org/10.3390/s22041651","pmid":"https://pubmed.ncbi.nlm.nih.gov/35214553"},"language":"en","primary_location":{"id":"doi:10.3390/s22041651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041651","pdf_url":"https://www.mdpi.com/1424-8220/22/4/1651/pdf?version=1645599601","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/4/1651/pdf?version=1645599601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088474393","display_name":"Weiheng Jiang","orcid":"https://orcid.org/0000-0002-1856-8337"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiheng Jiang","raw_affiliation_strings":["Communication Measurement and Control Center, Chongqing University, Chongqing 400044, China"],"raw_orcid":"https://orcid.org/0000-0002-1856-8337","affiliations":[{"raw_affiliation_string":"Communication Measurement and Control Center, Chongqing University, Chongqing 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060999711","display_name":"Wanxin Yu","orcid":"https://orcid.org/0000-0003-1641-2467"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxin Yu","raw_affiliation_strings":["Communication Measurement and Control Center, Chongqing University, Chongqing 400044, China"],"raw_orcid":"https://orcid.org/0000-0003-1641-2467","affiliations":[{"raw_affiliation_string":"Communication Measurement and Control Center, Chongqing University, Chongqing 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046054684","display_name":"Wenbo Wang","orcid":"https://orcid.org/0000-0002-7500-8723"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Wenbo Wang","raw_affiliation_strings":["Faculty of Engineering, Bar Ilan University, Ramat Gan 5290002, Israel"],"raw_orcid":"https://orcid.org/0000-0002-7500-8723","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar Ilan University, Ramat Gan 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100812902","display_name":"Tiancong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiancong Huang","raw_affiliation_strings":["School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100812902"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":2.1367,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87331982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"22","issue":"4","first_page":"1651","last_page":"1651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9993000030517578,"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9993000030517578,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.903577446937561},{"id":"https://openalex.org/keywords/cognitive-radio","display_name":"Cognitive radio","score":0.8632040023803711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7032199501991272},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5752962827682495},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5573093891143799},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5343329906463623},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5012471675872803},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48067793250083923},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4362596273422241},{"id":"https://openalex.org/keywords/cognitive-network","display_name":"Cognitive network","score":0.4251611530780792},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.41181039810180664},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36123424768447876},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3322731852531433},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3309803605079651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3156539797782898},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.15320849418640137},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13052937388420105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11941558122634888}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.903577446937561},{"id":"https://openalex.org/C149946192","wikidata":"https://www.wikidata.org/wiki/Q3235733","display_name":"Cognitive radio","level":3,"score":0.8632040023803711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032199501991272},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5752962827682495},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5573093891143799},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5343329906463623},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5012471675872803},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48067793250083923},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4362596273422241},{"id":"https://openalex.org/C32542511","wikidata":"https://www.wikidata.org/wiki/Q5141225","display_name":"Cognitive network","level":4,"score":0.4251611530780792},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.41181039810180664},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36123424768447876},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3322731852531433},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3309803605079651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156539797782898},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.15320849418640137},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13052937388420105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11941558122634888},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22041651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041651","pdf_url":"https://www.mdpi.com/1424-8220/22/4/1651/pdf?version=1645599601","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:35214553","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35214553","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:110fc7691c9c4a58952402804e360244","is_oa":true,"landing_page_url":"https://doaj.org/article/110fc7691c9c4a58952402804e360244","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 4, p 1651 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/4/1651/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22041651","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 22; Issue 4; Pages: 1651","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8879711","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8879711","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22041651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041651","pdf_url":"https://www.mdpi.com/1424-8220/22/4/1651/pdf?version=1645599601","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.5400000214576721,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6496091240","display_name":null,"funder_award_id":"62001067","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4213324132.pdf","grobid_xml":"https://content.openalex.org/works/W4213324132.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2032170999","https://openalex.org/W2076509460","https://openalex.org/W2103281825","https://openalex.org/W2109669601","https://openalex.org/W2145339207","https://openalex.org/W2148465836","https://openalex.org/W2203800991","https://openalex.org/W2285198146","https://openalex.org/W2342883192","https://openalex.org/W2746553466","https://openalex.org/W2786800736","https://openalex.org/W2883561198","https://openalex.org/W2901852491","https://openalex.org/W2911656593","https://openalex.org/W2930720221","https://openalex.org/W2944230110","https://openalex.org/W2959620113","https://openalex.org/W2969473779","https://openalex.org/W2969525674","https://openalex.org/W2991046523","https://openalex.org/W3007058358","https://openalex.org/W3011123090","https://openalex.org/W3013353193","https://openalex.org/W3015351299","https://openalex.org/W3016353205","https://openalex.org/W3032998286","https://openalex.org/W3036592597","https://openalex.org/W3037716954","https://openalex.org/W3046062522","https://openalex.org/W3090954451","https://openalex.org/W3191505721","https://openalex.org/W6774145759"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2277261328","https://openalex.org/W2610471112","https://openalex.org/W2167656028","https://openalex.org/W2101748387","https://openalex.org/W2800372944","https://openalex.org/W2340059876","https://openalex.org/W2010464513","https://openalex.org/W2732016385","https://openalex.org/W2915536052"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,22,41,53,57,63,70,73,76,93,125,129,145,159,165,170],"problem":[4,34,78,91],"of":[5,24,46,59,72,95,127],"distributed":[6],"spectrum/channel":[7],"access":[8],"for":[9,35],"cognitive":[10],"radio-enabled":[11],"unmanned":[12],"aerial":[13],"vehicles":[14],"(CUAVs)":[15],"that":[16,144],"overlay":[17],"upon":[18],"primary":[19,64],"channels.":[20],"Under":[21],"framework":[23,94],"cooperative":[25],"spectrum":[26],"sensing":[27],"and":[28,84,156,173],"opportunistic":[29],"transmission,":[30],"a":[31,82,100,136],"one-shot":[32],"optimization":[33],"channel":[36],"allocation,":[37],"aiming":[38],"to":[39,56,150,153],"maximize":[40],"expected":[42],"cumulative":[43],"weighted":[44],"reward":[45],"multiple":[47],"CUAVs,":[48],"is":[49,79,112,132],"formulated.":[50],"To":[51,123],"handle":[52],"uncertainty":[54],"due":[55],"lack":[58,71],"prior":[60],"knowledge":[61],"about":[62],"user":[65],"activities":[66],"as":[67,69,118,169],"well":[68],"channel-access":[74],"coordinator,":[75],"original":[77],"cast":[80],"into":[81],"competition":[83],"cooperation":[85],"hybrid":[86],"multi-agent":[87],"reinforcement":[88],"learning":[89],"(CCH-MARL)":[90],"in":[92],"Markov":[96],"game":[97],"(MG).":[98],"Then,":[99],"value-iteration-based":[101],"RL":[102],"algorithm,":[103],"which":[104],"features":[105],"upper":[106],"confidence":[107],"bound-Hoeffding":[108],"(UCB-H)":[109],"strategy":[110,131],"searching,":[111],"proposed":[113,146],"by":[114],"treating":[115],"each":[116],"CUAV":[117],"an":[119],"independent":[120],"learner":[121],"(IL).":[122],"address":[124],"curse":[126],"dimensionality,":[128],"UCB-H":[130],"further":[133],"extended":[134],"with":[135,164],"double":[137],"deep":[138],"Q-network":[139],"(DDQN).":[140],"Numerical":[141],"simulations":[142],"show":[143],"algorithms":[147,167],"are":[148],"able":[149],"efficiently":[151],"converge":[152],"stable":[154],"strategies,":[155],"significantly":[157],"improve":[158],"network":[160],"performance":[161],"when":[162],"compared":[163],"benchmark":[166],"such":[168],"vanilla":[171],"Q-learning":[172],"DDQN":[174],"algorithms.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}