{"id":"https://openalex.org/W4280514381","doi":"https://doi.org/10.1109/wcnc51071.2022.9771605","title":"On-Policy vs. Off-Policy Deep Reinforcement Learning for Resource Allocation in Open Radio Access Network","display_name":"On-Policy vs. Off-Policy Deep Reinforcement Learning for Resource Allocation in Open Radio Access Network","publication_year":2022,"publication_date":"2022-04-10","ids":{"openalex":"https://openalex.org/W4280514381","doi":"https://doi.org/10.1109/wcnc51071.2022.9771605"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc51071.2022.9771605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc51071.2022.9771605","pdf_url":null,"source":{"id":"https://openalex.org/S4363607776","display_name":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","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":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","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/A5014443856","display_name":"Nessrine Hammami","orcid":null},"institutions":[{"id":"https://openalex.org/I49663120","display_name":"Universit\u00e9 du Qu\u00e9bec","ror":"https://ror.org/010gxg263","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120"]},{"id":"https://openalex.org/I285663978","display_name":"Weatherford College","ror":"https://ror.org/02xwsbr93","country_code":"US","type":"education","lineage":["https://openalex.org/I285663978"]},{"id":"https://openalex.org/I4210117989","display_name":"Direction de la Recherche Technologique","ror":"https://ror.org/02ggzyd20","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I4210117989"]}],"countries":["CA","FR","US"],"is_corresponding":true,"raw_author_name":"Nessrine Hammami","raw_affiliation_strings":["University of Quebec,École de Technologie Supérieure (ÉTS),Canada","&#x00C9","cole de Technologie Sup&#x00E9","rieure (&#x00C9"],"affiliations":[{"raw_affiliation_string":"University of Quebec,École de Technologie Supérieure (ÉTS),Canada","institution_ids":["https://openalex.org/I49663120"]},{"raw_affiliation_string":"&#x00C9","institution_ids":["https://openalex.org/I285663978"]},{"raw_affiliation_string":"cole de Technologie Sup&#x00E9","institution_ids":["https://openalex.org/I4210117989"]},{"raw_affiliation_string":"rieure (&#x00C9","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019659545","display_name":"Kim Khoa Nguyen","orcid":"https://orcid.org/0000-0002-9354-7544"},"institutions":[{"id":"https://openalex.org/I4210117989","display_name":"Direction de la Recherche Technologique","ror":"https://ror.org/02ggzyd20","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I285663978","display_name":"Weatherford College","ror":"https://ror.org/02xwsbr93","country_code":"US","type":"education","lineage":["https://openalex.org/I285663978"]},{"id":"https://openalex.org/I49663120","display_name":"Universit\u00e9 du Qu\u00e9bec","ror":"https://ror.org/010gxg263","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120"]}],"countries":["CA","FR","US"],"is_corresponding":false,"raw_author_name":"Kim Khoa Nguyen","raw_affiliation_strings":["University of Quebec,École de Technologie Supérieure (ÉTS),Canada","cole de Technologie Sup&#x00E9","&#x00C9","rieure (&#x00C9"],"affiliations":[{"raw_affiliation_string":"University of Quebec,École de Technologie Supérieure (ÉTS),Canada","institution_ids":["https://openalex.org/I49663120"]},{"raw_affiliation_string":"cole de Technologie Sup&#x00E9","institution_ids":["https://openalex.org/I4210117989"]},{"raw_affiliation_string":"&#x00C9","institution_ids":["https://openalex.org/I285663978"]},{"raw_affiliation_string":"rieure (&#x00C9","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014443856"],"corresponding_institution_ids":["https://openalex.org/I285663978","https://openalex.org/I4210117989","https://openalex.org/I49663120"],"apc_list":null,"apc_paid":null,"fwci":6.111,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.98067633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1461","last_page":"1466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9997000098228455,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9997000098228455,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9987999796867371,"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/T10603","display_name":"Smart Grid Energy Management","score":0.996999979019165,"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":0.8607287406921387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8113524913787842},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6011968851089478},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.5963575839996338},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4973583519458771},{"id":"https://openalex.org/keywords/quality-of-experience","display_name":"Quality of experience","score":0.4896467328071594},{"id":"https://openalex.org/keywords/radio-access-network","display_name":"Radio access network","score":0.4478521943092346},{"id":"https://openalex.org/keywords/cellular-network","display_name":"Cellular network","score":0.4323866069316864},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.43036991357803345},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.41082578897476196},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.37294626235961914},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36180615425109863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2871987819671631},{"id":"https://openalex.org/keywords/base-station","display_name":"Base station","score":0.258233904838562},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17879006266593933}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8607287406921387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113524913787842},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6011968851089478},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.5963575839996338},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4973583519458771},{"id":"https://openalex.org/C2779333187","wikidata":"https://www.wikidata.org/wiki/Q3132648","display_name":"Quality of experience","level":3,"score":0.4896467328071594},{"id":"https://openalex.org/C106365562","wikidata":"https://www.wikidata.org/wiki/Q3078360","display_name":"Radio access network","level":4,"score":0.4478521943092346},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.4323866069316864},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.43036991357803345},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.41082578897476196},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.37294626235961914},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36180615425109863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2871987819671631},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.258233904838562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17879006266593933},{"id":"https://openalex.org/C207029474","wikidata":"https://www.wikidata.org/wiki/Q384018","display_name":"Mobile station","level":3,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wcnc51071.2022.9771605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc51071.2022.9771605","pdf_url":null,"source":{"id":"https://openalex.org/S4363607776","display_name":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","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":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:24829","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/24829/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Compte rendu de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2597068831","https://openalex.org/W2620671107","https://openalex.org/W2736601468","https://openalex.org/W2741401130","https://openalex.org/W2900804979","https://openalex.org/W2963095800","https://openalex.org/W2970759804","https://openalex.org/W3088599578","https://openalex.org/W3127503959","https://openalex.org/W3155580983","https://openalex.org/W3161037238","https://openalex.org/W3175656214","https://openalex.org/W4280514381","https://openalex.org/W6730111887","https://openalex.org/W6738741286","https://openalex.org/W6741002519","https://openalex.org/W6838133040"],"related_works":["https://openalex.org/W2029232111","https://openalex.org/W2159422359","https://openalex.org/W2762817092","https://openalex.org/W2294196761","https://openalex.org/W2141929741","https://openalex.org/W2335680976","https://openalex.org/W2252345849","https://openalex.org/W4252147399","https://openalex.org/W2805125868","https://openalex.org/W2923452570"],"abstract_inverted_index":{"Recently,":[0],"Deep":[1],"Reinforcement":[2],"Learning":[3],"(DRL)":[4],"has":[5],"increasingly":[6],"been":[7,31],"used":[8],"to":[9,33,48,58],"solve":[10],"complex":[11],"problems":[12],"in":[13,63,90],"mobile":[14],"networks.":[15],"There":[16],"are":[17,45],"two":[18],"main":[19],"types":[20],"of":[21,28,100],"DRL":[22,120],"models:":[23],"off-policy":[24,37,81,147],"and":[25,50,116,142],"on-policy.":[26],"Both":[27],"them":[29],"have":[30,34,51],"shown":[32],"advantages.":[35],"While":[36],"models":[38,44,121],"can":[39,134],"improve":[40],"sample":[41],"efficiency,":[42],"on-policy":[43,73,132],"generally":[46],"easy":[47],"implement":[49],"stable":[52],"performance.":[53],"Therefore,":[54],"it":[55],"becomes":[56],"hard":[57],"decide":[59],"the":[60,131,146],"appropriate":[61],"model":[62,133,148],"a":[64,92,97,123,136,150],"given":[65],"scenario.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"compare":[71],"an":[72,80,108],"model:":[74,82],"Proximal":[75],"Policy":[76],"Optimization":[77],"(PPO)":[78],"with":[79,86,114],"Sample":[83],"Efficient":[84],"Actor-Critic":[85],"Experience":[87],"Replay":[88],"(ACER)":[89],"solving":[91],"resource":[93],"allocation":[94],"problem":[95],"for":[96,107],"stringent":[98],"Quality":[99],"Service":[101],"(QoS)":[102],"application.":[103],"Results":[104],"show":[105],"that":[106,130],"Open":[109],"Radio":[110],"Access":[111],"Network":[112],"(O-RAN)":[113],"latency-sensitive":[115],"latency-tolerant":[117],"users,":[118],"both":[119],"outperform":[122],"greedy":[124],"algorithm.":[125],"We":[126],"also":[127],"point":[128],"out":[129],"guarantee":[135],"good":[137],"trade-off":[138],"between":[139],"energy":[140],"consumption":[141],"users":[143],"latency,":[144],"while":[145],"provides":[149],"faster":[151],"convergence.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}