{"id":"https://openalex.org/W3017042178","doi":"https://doi.org/10.1109/jiot.2020.2988268","title":"Accelerating Model-Free Reinforcement Learning With Imperfect Model Knowledge in Dynamic Spectrum Access","display_name":"Accelerating Model-Free Reinforcement Learning With Imperfect Model Knowledge in Dynamic Spectrum Access","publication_year":2020,"publication_date":"2020-04-16","ids":{"openalex":"https://openalex.org/W3017042178","doi":"https://doi.org/10.1109/jiot.2020.2988268","mag":"3017042178"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2020.2988268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2988268","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5058417610","display_name":"Lianjun Li","orcid":"https://orcid.org/0000-0002-1813-7764"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lianjun Li","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-1813-7764","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027237940","display_name":"Lingjia Liu","orcid":"https://orcid.org/0000-0003-1915-1784"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingjia Liu","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":"https://orcid.org/0000-0003-1915-1784","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063417397","display_name":"Jianan Bai","orcid":"https://orcid.org/0000-0002-7064-5280"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianan Bai","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-7064-5280","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067687694","display_name":"Hao-Hsuan Chang","orcid":"https://orcid.org/0000-0002-6910-054X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao-Hsuan Chang","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353673","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0001-6480-7976"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Standards and Mobility Innovation Lab, Samsung Research America, Plano, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Standards and Mobility Innovation Lab, Samsung Research America, Plano, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006871792","display_name":"Jonathan Ashdown","orcid":"https://orcid.org/0000-0001-7202-1095"},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan D. Ashdown","raw_affiliation_strings":["Information Directorate, Air Force Research Lab, Rome, USA"],"raw_orcid":"https://orcid.org/0000-0001-7202-1095","affiliations":[{"raw_affiliation_string":"Information Directorate, Air Force Research Lab, Rome, USA","institution_ids":["https://openalex.org/I1280414376"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442200","display_name":"Jianzhong Zhang","orcid":"https://orcid.org/0000-0001-8287-2512"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianzhong Zhang","raw_affiliation_strings":["Standards and Mobility Innovation Lab, Samsung Research America, Plano, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Standards and Mobility Innovation Lab, Samsung Research America, Plano, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018632091","display_name":"Yang Yi","orcid":"https://orcid.org/0000-0002-1354-0204"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yi","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-1354-0204","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5058417610"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.8726,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85681297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"8","first_page":"7517","last_page":"7528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","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"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9805999994277954,"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":0.8612068891525269},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8562148809432983},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4702673852443695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46809887886047363},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45683544874191284},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4391424357891083},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41277819871902466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3715946078300476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8612068891525269},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8562148809432983},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4702673852443695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46809887886047363},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45683544874191284},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4391424357891083},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41277819871902466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3715946078300476},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/jiot.2020.2988268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2988268","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5791444691","display_name":null,"funder_award_id":"ECCS-1811497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G927557786","display_name":null,"funder_award_id":"CCF-1937487","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1545148916","https://openalex.org/W1977655452","https://openalex.org/W1978114892","https://openalex.org/W1980035368","https://openalex.org/W2012587148","https://openalex.org/W2052190282","https://openalex.org/W2087617385","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2136204809","https://openalex.org/W2142819538","https://openalex.org/W2145339207","https://openalex.org/W2153620960","https://openalex.org/W2171671264","https://openalex.org/W2257979135","https://openalex.org/W2290354866","https://openalex.org/W2612336410","https://openalex.org/W2738669288","https://openalex.org/W2789824229","https://openalex.org/W2810754397","https://openalex.org/W2894110571","https://openalex.org/W2898754723","https://openalex.org/W2950471160","https://openalex.org/W2962872206","https://openalex.org/W2963079995","https://openalex.org/W2964295739","https://openalex.org/W2968764495","https://openalex.org/W3100844423","https://openalex.org/W4205513846","https://openalex.org/W4214717370","https://openalex.org/W4250589301","https://openalex.org/W4293396018","https://openalex.org/W6696324988","https://openalex.org/W6753264383"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2116157560","https://openalex.org/W2106714532","https://openalex.org/W2877093712","https://openalex.org/W4297979791","https://openalex.org/W4310614650"],"abstract_inverted_index":{"Current":[0],"studies":[1],"that":[2,99],"apply":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"to":[7,33,107],"dynamic":[8],"spectrum":[9],"access":[10],"(DSA)":[11],"problems":[12],"in":[13,24,40,76],"wireless":[14],"communications":[15],"systems":[16],"mainly":[17],"focus":[18],"on":[19],"model-free":[20,47,91],"RL":[21,50,133],"(MFRL).":[22],"However,":[23,75],"practice,":[25],"MFRL":[26,65,122,164,173],"requires":[27],"a":[28,59,77],"large":[29],"number":[30],"of":[31,62],"samples":[32],"achieve":[34],"good":[35],"performance":[36,63],"making":[37],"it":[38],"impractical":[39],"real-time":[41],"applications":[42],"such":[43],"as":[44,64,66,68],"DSA.":[45],"Combining":[46],"and":[48,92,95,124,134],"model-based":[49,93,132],"can":[51,100,169],"potentially":[52],"reduce":[53],"the":[54,69,80,109,120,125,142,146,150,156,163,172],"sample":[55,117],"complexity":[56,140],"while":[57,166],"achieving":[58],"similar":[60],"level":[61],"long":[67],"learned":[70,81,105,151],"model":[71,82,106,152],"is":[72,83,153],"accurate":[73],"enough.":[74],"complex":[78],"environment,":[79],"never":[84],"perfect.":[85],"In":[86],"this":[87],"article,":[88],"we":[89],"combine":[90],"RL,":[94],"introduce":[96],"an":[97,103],"algorithm":[98,114,123,127,130,158,165,168],"work":[101],"with":[102,136],"imperfectly":[104],"accelerate":[108],"MFRL.":[110],"Results":[111],"show":[112],"our":[113,167],"achieves":[115],"higher":[116],"efficiency":[118],"than":[119,141,162],"standard":[121,129],"Dyna":[126,143,157],"(a":[128],"integrating":[131],"MFRL)":[135],"much":[137],"lower":[138],"computation":[139],"algorithm.":[144,174],"For":[145],"extreme":[147],"case":[148],"where":[149],"highly":[154],"inaccurate,":[155],"performs":[159],"even":[160],"worse":[161],"still":[170],"outperform":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}