{"id":"https://openalex.org/W3205656755","doi":"https://doi.org/10.1109/tcomm.2021.3119689","title":"Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network","display_name":"Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network","publication_year":2021,"publication_date":"2021-10-14","ids":{"openalex":"https://openalex.org/W3205656755","doi":"https://doi.org/10.1109/tcomm.2021.3119689","mag":"3205656755"},"language":"en","primary_location":{"id":"doi:10.1109/tcomm.2021.3119689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcomm.2021.3119689","pdf_url":null,"source":{"id":"https://openalex.org/S196647941","display_name":"IEEE Transactions on Communications","issn_l":"0090-6778","issn":["0090-6778","1558-0857"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications","raw_type":"journal-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/A5037894061","display_name":"Yuanzhe Geng","orcid":"https://orcid.org/0000-0002-5865-2314"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhe Geng","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5865-2314","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034541026","display_name":"Erwu Liu","orcid":"https://orcid.org/0000-0002-2706-6208"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erwu Liu","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2706-6208","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431222","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-2974-0972"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2974-0972","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449908","display_name":"Yiming Liu","orcid":"https://orcid.org/0000-0002-1393-908X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Liu","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1393-908X","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":4.6509,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94754995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"70","issue":"1","first_page":"171","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10796","display_name":"Cooperative Communication and Network Coding","score":0.9998000264167786,"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/T10796","display_name":"Cooperative Communication and Network Coding","score":0.9998000264167786,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9968000054359436,"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/T11458","display_name":"Advanced Wireless Communication Technologies","score":0.9962999820709229,"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":0.8974710702896118},{"id":"https://openalex.org/keywords/relay","display_name":"Relay","score":0.8760412931442261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7273434400558472},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5124431252479553},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.48997846245765686},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47656965255737305},{"id":"https://openalex.org/keywords/channel-state-information","display_name":"Channel state information","score":0.4646695554256439},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4472881853580475},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4303792715072632},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42268964648246765},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3510909676551819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2689148187637329},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.2461344599723816},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19255253672599792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16719049215316772},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10666704177856445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0964832603931427}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8974710702896118},{"id":"https://openalex.org/C2778156585","wikidata":"https://www.wikidata.org/wiki/Q174053","display_name":"Relay","level":3,"score":0.8760412931442261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273434400558472},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5124431252479553},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.48997846245765686},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47656965255737305},{"id":"https://openalex.org/C148063708","wikidata":"https://www.wikidata.org/wiki/Q5072511","display_name":"Channel state information","level":3,"score":0.4646695554256439},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4472881853580475},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4303792715072632},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42268964648246765},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3510909676551819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2689148187637329},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.2461344599723816},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19255253672599792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16719049215316772},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10666704177856445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0964832603931427},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcomm.2021.3119689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcomm.2021.3119689","pdf_url":null,"source":{"id":"https://openalex.org/S196647941","display_name":"IEEE Transactions on Communications","issn_l":"0090-6778","issn":["0090-6778","1558-0857"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1500301389","display_name":null,"funder_award_id":"42171404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2425049952","display_name":null,"funder_award_id":"19511102002","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4717412138","display_name":null,"funder_award_id":"61771345","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1980310952","https://openalex.org/W2033644422","https://openalex.org/W2084779837","https://openalex.org/W2108427351","https://openalex.org/W2120448104","https://openalex.org/W2126080547","https://openalex.org/W2128295617","https://openalex.org/W2137809208","https://openalex.org/W2145339207","https://openalex.org/W2315140361","https://openalex.org/W2344445507","https://openalex.org/W2565358133","https://openalex.org/W2599312801","https://openalex.org/W2791110587","https://openalex.org/W2791781667","https://openalex.org/W2890860720","https://openalex.org/W2901561492","https://openalex.org/W2904491988","https://openalex.org/W2905026759","https://openalex.org/W2929863751","https://openalex.org/W2942184420","https://openalex.org/W2947622545","https://openalex.org/W2954168748","https://openalex.org/W2960729702","https://openalex.org/W2963060851","https://openalex.org/W2963761387","https://openalex.org/W2978207438","https://openalex.org/W2981559750","https://openalex.org/W3000245973","https://openalex.org/W3002189898","https://openalex.org/W3020522931","https://openalex.org/W3041207562","https://openalex.org/W3054258700","https://openalex.org/W3085955789","https://openalex.org/W3124919228","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6748638692","https://openalex.org/W6752089545","https://openalex.org/W6798659828"],"related_works":["https://openalex.org/W2539674285","https://openalex.org/W1998322187","https://openalex.org/W1038122923","https://openalex.org/W2952514781","https://openalex.org/W3019210376","https://openalex.org/W2519669146","https://openalex.org/W2561242965","https://openalex.org/W2463175948","https://openalex.org/W2006290459","https://openalex.org/W2465954300"],"abstract_inverted_index":{"In":[0,127],"this":[1],"paper,":[2],"we":[3,72,151,170],"study":[4],"the":[5,36,75,121,144,199,206,221,231,241],"outage":[6,18,232,243],"probability":[7,233],"minimizing":[8],"problem":[9,133],"in":[10,53,147,198,236],"a":[11,131,154,167],"two-hop":[12,237],"cooperative":[13],"relay":[14,26,181,238],"network.":[15],"To":[16],"reduce":[17,230],"probability,":[19],"existing":[20],"studies":[21],"propose":[22,153],"many":[23],"schemes":[24],"for":[25,81,97],"selection":[27,182],"and":[28,61,99,176,183,191,195,209,229],"power":[29,184],"allocation,":[30],"which":[31,140,162],"are":[32],"usually":[33],"based":[34],"on":[35],"assumption":[37],"of":[38,91],"exact":[39],"channel":[40,57],"state":[41],"information":[42],"(CSI).":[43],"However,":[44],"it":[45],"is":[46,124,130,141,163],"difficult":[47],"to":[48,74],"obtain":[49],"perfect":[50],"instantaneous":[51],"CSI":[52],"practical":[54],"situations":[55],"where":[56],"states":[58],"change":[59],"rapidly,":[60],"thus":[62],"traditional":[63,218],"methods":[64,80,84,197],"would":[65],"not":[66,86],"perform":[67,118],"well.":[68],"Considering":[69],"these":[70],"factors,":[71],"turn":[73],"emerging":[76],"reinforcement":[77,113,137],"learning":[78,114,138],"(RL)":[79],"solutions.":[82],"RL":[83,108],"do":[85],"need":[87],"any":[88],"prior":[89],"knowledge":[90],"CSI,":[92],"but":[93],"use":[94],"neural":[95],"network":[96,239],"approximation":[98],"decision":[100],"after":[101],"interacting":[102],"with":[103,157,217,240],"communication":[104],"environment.":[105],"Nevertheless,":[106],"conventional":[107],"methods,":[109,116],"including":[110],"most":[111],"deep":[112],"(DRL)":[115],"cannot":[117],"well":[119],"when":[120,134],"search":[122],"space":[123],"too":[125],"large.":[126],"addition,":[128],"non-stationarity":[129],"common":[132],"using":[135],"hierarchical":[136,188],"(HRL),":[139],"caused":[142],"by":[143,234],"changing":[145],"behavior":[146],"different":[148],"hierarchies.":[149],"Therefore,":[150],"first":[152],"DRL":[155,219],"framework":[156,175],"an":[158,173],"outage-based":[159],"reward":[160,208],"function,":[161],"then":[164],"used":[165],"as":[166],"baseline.":[168],"Then,":[169],"further":[171],"design":[172],"HRL":[174,200,223],"training":[177,224],"algorithm.":[178],"By":[179],"decomposing":[180],"allocation":[185],"into":[186],"two":[187],"optimization":[189],"objectives,":[190],"combining":[192],"on-":[193],"policy":[194],"off-policy":[196],"framework,":[201],"our":[202],"method":[203],"successfully":[204],"address":[205],"sparse":[207],"non-stationary":[210],"problem.":[211],"Simulation":[212],"results":[213],"reveal":[214],"that":[215],"compared":[216],"method,":[220],"proposed":[222],"algorithm":[225],"can":[226],"converge":[227],"faster":[228],"8%":[235],"same":[242],"threshold.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}