{"id":"https://openalex.org/W4214854086","doi":"https://doi.org/10.1109/twc.2022.3153175","title":"Distributed Deep Reinforcement Learning-Based Spectrum and Power Allocation for Heterogeneous Networks","display_name":"Distributed Deep Reinforcement Learning-Based Spectrum and Power Allocation for Heterogeneous Networks","publication_year":2022,"publication_date":"2022-03-02","ids":{"openalex":"https://openalex.org/W4214854086","doi":"https://doi.org/10.1109/twc.2022.3153175"},"language":"en","primary_location":{"id":"doi:10.1109/twc.2022.3153175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2022.3153175","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Wireless Communications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/166422/2/Distributed%20Deep%20Reinforcement%20Learning-Based%20Spectrum%20and%20Power%20Allocation%20for%20Heterogeneous%20Networks.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013729643","display_name":"Helin Yang","orcid":"https://orcid.org/0000-0001-9697-7470"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Helin Yang","raw_affiliation_strings":["Strategic Centre for Research in Privacy-Preserving Technologies and Systems, Nanyang Technological University, Singapore","Department of Information and Communication Engineering, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Strategic Centre for Research in Privacy-Preserving Technologies and Systems, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071321132","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0002-3004-7091"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101720092","display_name":"Kwok\u2010Yan Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kwok-Yan Lam","raw_affiliation_strings":["School of Computer Science and Engineering and the Strategic Centre for Research in Privacy-Preserving Technologies and Systems, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Strategic Centre for Research in Privacy-Preserving Technologies and Systems, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005327587","display_name":"Zehui Xiong","orcid":"https://orcid.org/0000-0002-4440-941X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zehui Xiong","raw_affiliation_strings":["Pillar of Information Systems Technology and Design, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Pillar of Information Systems Technology and Design, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048817096","display_name":"Qingqing Wu","orcid":"https://orcid.org/0000-0002-0043-3266"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Qingqing Wu","raw_affiliation_strings":["State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068976123","display_name":"Liang Xiao","orcid":"https://orcid.org/0000-0003-2402-611X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xiao","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013729643"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":10.5624,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98750628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"21","issue":"9","first_page":"6935","last_page":"6948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9994000196456909,"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/T13553","display_name":"Age of Information Optimization","score":0.9994000196456909,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9947999715805054,"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"}},{"id":"https://openalex.org/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9871000051498413,"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/computer-science","display_name":"Computer science","score":0.8416849374771118},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8339285254478455},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7360488772392273},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7350473403930664},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6244339942932129},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.5596538782119751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.506093442440033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4370119571685791},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4284118115901947},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.29167747497558594},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24697420001029968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416849374771118},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8339285254478455},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7360488772392273},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7350473403930664},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6244339942932129},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.5596538782119751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.506093442440033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4370119571685791},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4284118115901947},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.29167747497558594},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24697420001029968},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/twc.2022.3153175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2022.3153175","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Wireless Communications","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/166422","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/166422","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/166422/2/Distributed%20Deep%20Reinforcement%20Learning-Based%20Spectrum%20and%20Power%20Allocation%20for%20Heterogeneous%20Networks.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/166422","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/166422","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/166422/2/Distributed%20Deep%20Reinforcement%20Learning-Based%20Spectrum%20and%20Power%20Allocation%20for%20Heterogeneous%20Networks.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2060661075","display_name":null,"funder_award_id":"U21A2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2208840198","display_name":null,"funder_award_id":"DeST-SCI2019-0012","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G2728353108","display_name":null,"funder_award_id":"SRG-ISTD-2021-165","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G2874061861","display_name":null,"funder_award_id":"61971366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2884910486","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320322724","funder_display_name":"Ministry of Education, India"},{"id":"https://openalex.org/G3011155338","display_name":null,"funder_award_id":"202102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G301330796","display_name":null,"funder_award_id":"Start","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G3048563442","display_name":null,"funder_award_id":"Tier 1","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4009049029","display_name":null,"funder_award_id":"Startup","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4538315278","display_name":null,"funder_award_id":"SUTD-ZJU IDEA","funder_id":"https://openalex.org/F4320324110","funder_display_name":"Singapore University of Technology and Design"},{"id":"https://openalex.org/G5570204100","display_name":null,"funder_award_id":"U21A204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7203450436","display_name":null,"funder_award_id":"U21A20444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8050651220","display_name":null,"funder_award_id":"202101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8669559347","display_name":null,"funder_award_id":"SRG-ISTD-2021-165","funder_id":"https://openalex.org/F4320324110","funder_display_name":"Singapore University of Technology and Design"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4214854086.pdf","grobid_xml":"https://content.openalex.org/works/W4214854086.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2046979221","https://openalex.org/W2125890412","https://openalex.org/W2483325812","https://openalex.org/W2528522595","https://openalex.org/W2578743652","https://openalex.org/W2607844664","https://openalex.org/W2618666182","https://openalex.org/W2744524871","https://openalex.org/W2779774899","https://openalex.org/W2788115019","https://openalex.org/W2793960410","https://openalex.org/W2808015125","https://openalex.org/W2883265677","https://openalex.org/W2898841794","https://openalex.org/W2916079228","https://openalex.org/W2922273628","https://openalex.org/W2963050357","https://openalex.org/W2963232267","https://openalex.org/W2964129085","https://openalex.org/W2967959654","https://openalex.org/W2968522222","https://openalex.org/W2968782695","https://openalex.org/W2989639897","https://openalex.org/W2991301449","https://openalex.org/W2991544738","https://openalex.org/W2999146029","https://openalex.org/W3004171315","https://openalex.org/W3006762012","https://openalex.org/W3009908063","https://openalex.org/W3010100380","https://openalex.org/W3010141230","https://openalex.org/W3013745173","https://openalex.org/W3016282456","https://openalex.org/W3035796478","https://openalex.org/W3038758569","https://openalex.org/W3040668711","https://openalex.org/W3047909149","https://openalex.org/W3048280785","https://openalex.org/W3089283090","https://openalex.org/W3094019951","https://openalex.org/W3098133185","https://openalex.org/W3103493968","https://openalex.org/W3153098216","https://openalex.org/W3168104141","https://openalex.org/W3169992717","https://openalex.org/W3217746782","https://openalex.org/W4214717370","https://openalex.org/W6687681856","https://openalex.org/W6749032143"],"related_works":["https://openalex.org/W3091825588","https://openalex.org/W3094198577","https://openalex.org/W4299796970","https://openalex.org/W2947076271","https://openalex.org/W3094091075","https://openalex.org/W4221147568","https://openalex.org/W2969525674","https://openalex.org/W3085733781","https://openalex.org/W2129464557","https://openalex.org/W4206444456"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,37,59,62,89,96,104,110,117,125,132,139],"problem":[4,39],"of":[5,152],"distributed":[6,81,118,141],"resource":[7,92],"management":[8,93],"in":[9,150],"two-tier":[10],"heterogeneous":[11],"networks,":[12],"where":[13,95],"each":[14],"cell":[15],"selects":[16],"its":[17],"joint":[18],"device":[19],"association,":[20],"spectrum":[21],"allocation,":[22],"and":[23,47,70,112,122,158],"power":[24],"allocation":[25],"strategy":[26],"based":[27],"only":[28],"on":[29],"locally-observed":[30],"information":[31],"without":[32],"any":[33],"central":[34],"controller.":[35],"As":[36],"optimization":[38],"with":[40,67,80],"devices\u2019":[41],"quality-of-service":[42],"(QoS)":[43],"constraints":[44],"is":[45,64,84],"non-convex":[46],"NP-hard,":[48],"we":[49],"model":[50],"it":[51],"as":[52],"a":[53,73],"Markov":[54],"decision":[55],"process":[56],"(MDP).":[57],"Considering":[58],"fact":[60],"that":[61,138],"network":[63,101,155],"highly":[65],"complex":[66],"large":[68],"state":[69],"action":[71,113],"spaces,":[72],"multi-agent":[74],"dueling":[75,99,123],"deep-Q":[76],"network-based":[77],"algorithm":[78,97,127,144],"combined":[79],"coordinated":[82,119,142],"learning":[83,120,126,143,148,153],"proposed":[85,140],"to":[86,102,131],"effectively":[87],"learn":[88,103],"optimized":[90,133],"intelligent":[91],"policy,":[94],"adopts":[98],"deep":[100],"action-value":[105],"distribution":[106],"by":[107],"estimating":[108],"both":[109],"state-value":[111],"advantage":[114],"functions.":[115],"Under":[116],"manner":[121],"architecture,":[124],"can":[128],"rapidly":[129],"converge":[130],"policy.":[134],"Simulation":[135],"results":[136],"demonstrate":[137],"outperforms":[145],"other":[146],"existing":[147],"algorithms":[149],"terms":[151],"efficiency,":[154],"data":[156],"rate,":[157],"QoS":[159],"satisfaction":[160],"probability.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}