{"id":"https://openalex.org/W4393379922","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477008","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":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393379922","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477008"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10477008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10477008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","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/A5100435639","display_name":"Kun Yang","orcid":"https://orcid.org/0000-0002-6782-6689"},"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":["University of Virginia,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, 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":["University of Virginia,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, 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":["The Pennsylvania State University,Department of Electrical Engineering,USA","Department of Electrical Engineering, The Pennsylvania State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Pennsylvania State University, 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,USA","Intel Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114101923","display_name":"Jerry Sydir","orcid":null},"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":"Jerry Sydir","raw_affiliation_strings":["Intel Corporation,USA","Intel Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.569,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70507765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11158","display_name":"Wireless Networks and Protocols","score":0.98580002784729,"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":0.98580002784729,"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":0.9768000245094299,"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":0.9598000049591064,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.805144190788269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7454148530960083},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5721586346626282},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.48710012435913086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521106779575348},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42168670892715454},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3325265049934387},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10796868801116943}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.805144190788269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454148530960083},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5721586346626282},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.48710012435913086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521106779575348},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42168670892715454},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3325265049934387},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10796868801116943}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10477008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10477008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2103723095","https://openalex.org/W2103724767","https://openalex.org/W2110621360","https://openalex.org/W2904246096","https://openalex.org/W2943020286","https://openalex.org/W2962841091","https://openalex.org/W2969195240","https://openalex.org/W2970269258","https://openalex.org/W3005761304","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3048446347","https://openalex.org/W3123582921","https://openalex.org/W3138939485","https://openalex.org/W3170697419","https://openalex.org/W3205794883","https://openalex.org/W4223423875","https://openalex.org/W6757469721","https://openalex.org/W6762058563","https://openalex.org/W6776438516","https://openalex.org/W6779265984","https://openalex.org/W6796971187","https://openalex.org/W6802659552","https://openalex.org/W6810653392","https://openalex.org/W6853515959"],"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],"recent":[1],"development":[2],"of":[3,11,54,94,107,148],"reinforcement":[4],"learning":[5],"(RL)":[6],"has":[7],"boosted":[8],"the":[9,28,35,41,52,60,105,111,117,149],"adoption":[10],"online":[12,21],"RL":[13,22,56,68,109,130,152,157],"for":[14,82,110,121],"wireless":[15],"radio":[16],"resource":[17],"management":[18],"(RRM).":[19],"However,":[20],"algorithms":[23,57],"require":[24],"direct":[25],"interactions":[26],"with":[27,144],"environment,":[29],"which":[30],"may":[31],"be":[32],"undesirable":[33],"given":[34],"potential":[36],"performance":[37,106],"loss":[38],"due":[39],"to":[40],"unavoidable":[42],"exploration":[43],"in":[44,58],"RL.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"first":[50],"investigate":[51],"use":[53],"offline":[55,67,108,129,151],"solving":[59],"RRM":[61,85,112],"problem.":[62],"We":[63,102,141],"evaluate":[64],"several":[65],"state-of-the-art":[66],"algorithms,":[69],"including":[70],"behavior":[71,118,139,163],"constrained":[72],"Q-Iearning":[73],"(BCQ),":[74],"conservative":[75],"Q-learning":[76,80],"(CQL),":[77],"and":[78,96,124],"implicit":[79],"(IQL),":[81],"a":[83,91,127,145,155],"specific":[84],"problem":[86,113],"that":[87,104,132,143],"aims":[88],"at":[89],"maximizing":[90],"linear":[92],"combination":[93],"sum":[95],"5-percentile":[97],"rates":[98],"via":[99],"user":[100],"scheduling.":[101],"observe":[103],"depends":[114],"critically":[115],"on":[116],"policy":[119,158],"used":[120],"data":[122],"collection,":[123],"further":[125],"propose":[126],"novel":[128],"solution":[131],"leverages":[133],"heterogeneous":[134],"datasets":[135],"collected":[136],"by":[137],"different":[138],"policies.":[140],"show":[142],"proper":[146],"mixture":[147],"datasets,":[150],"can":[153],"produce":[154],"near-optimal":[156],"even":[159],"when":[160],"all":[161],"involved":[162],"policies":[164],"are":[165],"highly":[166],"suboptimal.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}