{"id":"https://openalex.org/W4384161820","doi":"https://doi.org/10.1109/lwc.2023.3294910","title":"Deep Reinforcement Learning for Improving Resource Utilization Efficiency of URLLC With Imperfect Channel State Information","display_name":"Deep Reinforcement Learning for Improving Resource Utilization Efficiency of URLLC With Imperfect Channel State Information","publication_year":2023,"publication_date":"2023-07-13","ids":{"openalex":"https://openalex.org/W4384161820","doi":"https://doi.org/10.1109/lwc.2023.3294910"},"language":"en","primary_location":{"id":"doi:10.1109/lwc.2023.3294910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2023.3294910","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications Letters","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/A5068388572","display_name":"Litianyi Zhang","orcid":"https://orcid.org/0000-0002-4099-3057"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Litianyi Zhang","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079772530","display_name":"Changyang She","orcid":"https://orcid.org/0000-0003-0193-9784"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Changyang She","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029622571","display_name":"Kai Ying","orcid":"https://orcid.org/0000-0003-2645-5305"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Ying","raw_affiliation_strings":["School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448724","display_name":"Yonghui Li","orcid":"https://orcid.org/0000-0001-7702-1123"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yonghui Li","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043371405","display_name":"Branka Vucetic","orcid":"https://orcid.org/0000-0002-2700-2001"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Branka Vucetic","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068388572"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.8023,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71570639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"12","issue":"10","first_page":"1796","last_page":"1800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10964","display_name":"Wireless Communication Security Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10964","display_name":"Wireless Communication Security Techniques","score":0.9998999834060669,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9973000288009644,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7902886867523193},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7102753520011902},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.640004575252533},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5721976161003113},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5029613375663757},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.46474072337150574},{"id":"https://openalex.org/keywords/channel-state-information","display_name":"Channel state information","score":0.46349477767944336},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.44137483835220337},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4413193464279175},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3925696909427643},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.3391157388687134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2434946596622467},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10601809620857239},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10258975625038147},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09655743837356567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902886867523193},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7102753520011902},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.640004575252533},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5721976161003113},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5029613375663757},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.46474072337150574},{"id":"https://openalex.org/C148063708","wikidata":"https://www.wikidata.org/wiki/Q5072511","display_name":"Channel state information","level":3,"score":0.46349477767944336},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.44137483835220337},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4413193464279175},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3925696909427643},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.3391157388687134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2434946596622467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10601809620857239},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10258975625038147},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09655743837356567},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lwc.2023.3294910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2023.3294910","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G8234242040","display_name":null,"funder_award_id":"DE210100415","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2036533317","https://openalex.org/W2106864314","https://openalex.org/W2130134073","https://openalex.org/W2157293015","https://openalex.org/W2433339266","https://openalex.org/W2787938642","https://openalex.org/W2963864421","https://openalex.org/W2996396177","https://openalex.org/W3054393695","https://openalex.org/W3112324757","https://openalex.org/W3134502172","https://openalex.org/W3135089279","https://openalex.org/W3137706447","https://openalex.org/W3143519386","https://openalex.org/W3162902207","https://openalex.org/W3168692131","https://openalex.org/W4220874105","https://openalex.org/W4226115189","https://openalex.org/W4250589301","https://openalex.org/W4285170701","https://openalex.org/W4313350218","https://openalex.org/W6684921986","https://openalex.org/W6687063787","https://openalex.org/W6748839928","https://openalex.org/W6796690604"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"This":[0],"letter":[1],"optimizes":[2],"resource":[3,28,159],"blocks":[4],"allocated":[5],"for":[6,121],"channel":[7,48,117,127,135],"estimation":[8,49],"and":[9,14,46,105,112,129,153],"data":[10],"transmission":[11],"in":[12,42,158],"multiple-input":[13],"single-output":[15],"(MISO)":[16],"ultra-reliable":[17],"low-latency":[18],"communication":[19],"(URLLC)":[20],"systems.":[21],"The":[22,137],"goal":[23],"is":[24,50,55,66],"to":[25,32,163],"improve":[26],"the":[27,43,47,53,97,123,130,142,150,164],"utilization":[29,160],"efficiency":[30,161],"subject":[31],"a":[33,58,67,80,101,109],"reliability":[34],"constraint.":[35],"Considering":[36],"that":[37,141],"wireless":[38],"channels":[39],"are":[40,119],"correlated":[41,126],"temporal":[44],"domain,":[45],"not":[51],"error-free,":[52],"problem":[54,70],"formulated":[56],"as":[57],"partial":[59,72],"observation":[60],"Markov":[61],"decision":[62],"process":[63],"(POMDP),":[64],"which":[65],"sequential":[68],"decision-making":[69],"with":[71,108],"observations.":[73],"To":[74],"solve":[75],"this":[76],"problem,":[77],"we":[78],"develop":[79],"constrained":[81],"deep":[82],"reinforcement":[83],"learning":[84],"(DRL)":[85],"algorithm,":[86],"namely":[87],"Cascaded-Action":[88],"Twin":[89],"Delayed":[90],"Deep":[91],"Deterministic":[92],"policy":[93,98],"(CA-TD3).":[94],"We":[95],"train":[96],"by":[99],"using":[100],"primal":[102,144],"domain":[103],"method":[104,111,146,152],"compare":[106],"it":[107],"primal-dual":[110,151],"an":[113],"existing":[114],"benchmark.":[115,165],"Two":[116],"models":[118],"considered":[120],"evaluation:":[122],"first-order":[124],"autoregressive":[125],"model":[128],"clustered":[131],"delay":[132],"line":[133],"(CDL)":[134],"model.":[136],"simulation":[138],"results":[139],"show":[140],"proposed":[143],"CA-TD3":[145],"converges":[147],"faster":[148],"than":[149],"achieves":[154],"over":[155],"30%":[156],"improvement":[157],"compared":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}