{"id":"https://openalex.org/W7163217872","doi":"https://doi.org/10.1109/lnet.2026.3699505","title":"Delay-Aware Reinforcement Learning for O-RAN Control Under Stochastic Reward Feedback","display_name":"Delay-Aware Reinforcement Learning for O-RAN Control Under Stochastic Reward Feedback","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163217872","doi":"https://doi.org/10.1109/lnet.2026.3699505"},"language":null,"primary_location":{"id":"doi:10.1109/lnet.2026.3699505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lnet.2026.3699505","pdf_url":null,"source":{"id":"https://openalex.org/S4210234060","display_name":"IEEE Networking Letters","issn_l":"2576-3156","issn":["2576-3156"],"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 Networking 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/A5102686427","display_name":"Xingqi Wu","orcid":"https://orcid.org/0009-0006-3044-6080"},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingqi Wu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Michigan–Dearborn, Dearborn, MI, USA"],"raw_orcid":"https://orcid.org/0009-0006-3044-6080","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Michigan–Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123381532","display_name":"Junaid Farooq","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junaid Farooq","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Michigan–Dearborn, Dearborn, MI, USA"],"raw_orcid":"https://orcid.org/0000-0003-0618-9345","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Michigan–Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066567675","display_name":"T K L Li","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Department of Systems Engineering, City University of Hong Kong, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8966-7239","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137639893","display_name":"Juntao Chen","orcid":"https://orcid.org/0000-0001-7726-4926"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juntao Chen","raw_affiliation_strings":["Department of Computer and Information Science, Fordham University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-7726-4926","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137642415","display_name":"Ying Wang","orcid":"https://orcid.org/0000-0002-9004-7253"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["Department of Systems Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-9004-7253","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69232897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"263","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.28459998965263367,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.28459998965263367,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.18520000576972961,"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.08009999990463257,"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":0.576200008392334},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5522000193595886},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3962000012397766},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.36730000376701355},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3179999887943268},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6090999841690063},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41940000653266907},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lnet.2026.3699505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lnet.2026.3699505","pdf_url":null,"source":{"id":"https://openalex.org/S4210234060","display_name":"IEEE Networking Letters","issn_l":"2576-3156","issn":["2576-3156"],"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 Networking Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4085730314254761}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-06-03T00:00:00"}