{"id":"https://openalex.org/W4396817492","doi":"https://doi.org/10.1109/twc.2024.3395624","title":"Offline Reinforcement Learning for Wireless Network Optimization With Mixture Datasets","display_name":"Offline Reinforcement Learning for Wireless Network Optimization With Mixture Datasets","publication_year":2024,"publication_date":"2024-05-10","ids":{"openalex":"https://openalex.org/W4396817492","doi":"https://doi.org/10.1109/twc.2024.3395624"},"language":"en","primary_location":{"id":"doi:10.1109/twc.2024.3395624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2024.3395624","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101662195","display_name":"Kun Yang","orcid":"https://orcid.org/0000-0002-9714-4291"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9714-4291","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082788397","display_name":"Chengshuai Shi","orcid":"https://orcid.org/0000-0002-2727-8251"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengshuai Shi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2727-8251","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016749653","display_name":"Cong Shen","orcid":"https://orcid.org/0000-0002-3148-4453"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3148-4453","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645589","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-6009-864X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Department of Electrical Engineering, The Pennsylvania State University, State College, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6009-864X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032337158","display_name":"Shu\u2010ping Yeh","orcid":"https://orcid.org/0000-0001-5255-2681"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu-Ping Yeh","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5255-2681","affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113534922","display_name":"Jaroslaw J. Sydir","orcid":"https://orcid.org/0009-0005-6493-7710"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaroslaw J. Sydir","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-6493-7710","affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9954,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95647506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"23","issue":"10","first_page":"12703","last_page":"12716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11158","display_name":"Wireless Networks and Protocols","score":0.9872999787330627,"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/T11158","display_name":"Wireless Networks and Protocols","score":0.9872999787330627,"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":0.9779999852180481,"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/T10796","display_name":"Cooperative Communication and Network Coding","score":0.9589999914169312,"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":0.7783243656158447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7582862377166748},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5874698162078857},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5667452812194824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4674677848815918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4345686435699463},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3236119747161865},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1391540765762329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783243656158447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7582862377166748},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5874698162078857},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5667452812194824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4674677848815918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4345686435699463},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3236119747161865},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1391540765762329}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/twc.2024.3395624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2024.3395624","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2364766549","display_name":null,"funder_award_id":"CNS-2003131","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2427936041","display_name":null,"funder_award_id":"ECCS-2030026","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4863430244","display_name":null,"funder_award_id":"ECCS-2143559","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7083397504","display_name":null,"funder_award_id":"ECCS-2029978","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7170065420","display_name":null,"funder_award_id":"SII-2132700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7934005977","display_name":null,"funder_award_id":"CNS-2002902","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":61,"referenced_works":["https://openalex.org/W2001203190","https://openalex.org/W2103723095","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2767313115","https://openalex.org/W2791827017","https://openalex.org/W2904246096","https://openalex.org/W2914552210","https://openalex.org/W2943020286","https://openalex.org/W2959895084","https://openalex.org/W2962841091","https://openalex.org/W2969195240","https://openalex.org/W2970269258","https://openalex.org/W3005761304","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3048446347","https://openalex.org/W3123582921","https://openalex.org/W3124816456","https://openalex.org/W3169600468","https://openalex.org/W3205794883","https://openalex.org/W4223423875","https://openalex.org/W4226048154","https://openalex.org/W4287756699","https://openalex.org/W4306295215","https://openalex.org/W4323521126","https://openalex.org/W4323927473","https://openalex.org/W4361865079","https://openalex.org/W4377089802","https://openalex.org/W4388667008","https://openalex.org/W4392591475","https://openalex.org/W4393379922","https://openalex.org/W4401693572","https://openalex.org/W6677067356","https://openalex.org/W6695011786","https://openalex.org/W6741002519","https://openalex.org/W6745497480","https://openalex.org/W6757469721","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6780571964","https://openalex.org/W6787043984","https://openalex.org/W6789305357","https://openalex.org/W6792120457","https://openalex.org/W6796971187","https://openalex.org/W6797702751","https://openalex.org/W6801801719","https://openalex.org/W6802659552","https://openalex.org/W6810653392","https://openalex.org/W6811051195","https://openalex.org/W6838915746","https://openalex.org/W6846298114","https://openalex.org/W6846557978","https://openalex.org/W6850790624","https://openalex.org/W6851438524","https://openalex.org/W6853304024","https://openalex.org/W6853515959","https://openalex.org/W6856810907","https://openalex.org/W6860031884"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2908230797"],"abstract_inverted_index":{"The":[0,194],"recent":[1],"development":[2],"of":[3,11,54,84,99,138,183,191],"reinforcement":[4],"learning":[5],"(RL)":[6],"has":[7],"boosted":[8],"the":[9,28,35,41,52,62,97,103,110,189,205],"adoption":[10],"online":[12,21,185],"RL":[13,22,58,70,101,122,142,186],"for":[14,72,102,114,169],"wireless":[15],"radio":[16],"resource":[17],"management":[18],"(RRM).":[19],"However,":[20],"algorithms":[23,59,71],"require":[24],"direct":[25],"interactions":[26],"with":[27,146,214],"environment,":[29],"which":[30],"may":[31],"be":[32],"undesirable":[33],"given":[34],"potential":[36],"performance":[37,98],"loss":[38],"due":[39],"to":[40,158,172,204],"unavoidable":[42],"exploration":[43],"in":[44,60,188,223],"RL.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,151],"first":[50],"explore":[51],"use":[53],"<italic":[55],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">offline</i>":[57],"solving":[61],"RRM":[63,75,104],"problem.":[64,227],"We":[65,117],"evaluate":[66],"several":[67],"state-of-the-art":[68],"offline":[69,100,121],"a":[73,81,135,165],"practical":[74],"problem":[76,105],"that":[77,96,134],"aims":[78],"at":[79],"maximizing":[80],"linear":[82],"combination":[83],"total":[85],"rates":[86,89],"and":[87,164],"5-percentile":[88],"via":[90],"user":[91,225],"scheduling.":[92],"Our":[93,175],"findings":[94],"indicate":[95],"is":[106],"heavily":[107],"contingent":[108],"upon":[109],"behavior":[111,129,148],"policy":[112,143,157],"deployed":[113],"data":[115,176,206],"collection.":[116],"propose":[118],"an":[119,155,184],"innovative":[120],"approach":[123,178],"utilizing":[124],"heterogeneous":[125],"datasets":[126,139],"from":[127],"various":[128],"policies.":[130,149],"This":[131],"method":[132],"demonstrates":[133],"strategic":[136],"mixture":[137,161,177,207],"enables":[140],"near-optimal":[141],"generation,":[144],"even":[145],"suboptimal":[147],"Additionally,":[150],"introduce":[152],"two":[153],"enhancements:":[154],"ensemble-based":[156],"augment":[159],"dataset":[160],"training":[162,199],"efficiency,":[163],"novel":[166],"offline-to-online":[167,215],"strategy":[168],"seamless":[170],"adaptation":[171],"new":[173],"environments.":[174],"achieves":[179],"over":[180],"95%":[181],"efficiency":[182],"agent":[187],"absence":[190],"expert":[192],"data.":[193],"ensemble":[195],"algorithm":[196],"notably":[197],"reduces":[198],"duration":[200],"by":[201,220],"half":[202],"compared":[203],"method.":[208],"Furthermore,":[209],"our":[210,224],"model,":[211],"when":[212],"applied":[213],"fine-tuning,":[216],"surpasses":[217],"existing":[218],"benchmarks":[219],"approximately":[221],"5%":[222],"scheduling":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}