{"id":"https://openalex.org/W4415482172","doi":"https://doi.org/10.1109/tsp.2025.3624833","title":"Provable Performance Bounds for Digital Twin-Driven Reinforcement Learning in Wireless Networks: A Novel Digital-Twin Bisimulation Metric","display_name":"Provable Performance Bounds for Digital Twin-Driven Reinforcement Learning in Wireless Networks: A Novel Digital-Twin Bisimulation Metric","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415482172","doi":"https://doi.org/10.1109/tsp.2025.3624833"},"language":null,"primary_location":{"id":"doi:10.1109/tsp.2025.3624833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3624833","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","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/A5102898516","display_name":"Zhenyu Tao","orcid":"https://orcid.org/0000-0002-8586-4179"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Tao","raw_affiliation_strings":["National Mobile Communications Research Lab, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Lab, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407852","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-1960-0992"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["National Mobile Communications Research Lab, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Lab, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072916702","display_name":"Xiaohu You","orcid":"https://orcid.org/0000-0002-0809-8511"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu You","raw_affiliation_strings":["National Mobile Communications Research Lab, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Lab, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102898516"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31507581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":null,"first_page":"4430","last_page":"4445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10784","display_name":"Muscle activation and electromyography studies","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10558","display_name":"Advancements in Semiconductor Devices and Circuit Design","score":0.9476000070571899,"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/T10187","display_name":"Radio Frequency Integrated Circuit Design","score":0.9289000034332275,"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/metric","display_name":"Metric (unit)","score":0.6801999807357788},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6000000238418579},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5952000021934509},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5666999816894531},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5396000146865845},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.53329998254776},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.49070000648498535},{"id":"https://openalex.org/keywords/bisimulation","display_name":"Bisimulation","score":0.4390999972820282},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43810001015663147}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6801999807357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352999806404114},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5666999816894531},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5396000146865845},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C135315306","wikidata":"https://www.wikidata.org/wiki/Q866364","display_name":"Bisimulation","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31949999928474426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C94523657","wikidata":"https://www.wikidata.org/wiki/Q4085781","display_name":"Wireless ad hoc network","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2025.3624833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3624833","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1458771408","https://openalex.org/W1504915502","https://openalex.org/W1585160083","https://openalex.org/W1967036113","https://openalex.org/W1995688924","https://openalex.org/W2032938251","https://openalex.org/W2046213250","https://openalex.org/W2103012681","https://openalex.org/W2107726111","https://openalex.org/W2165698076","https://openalex.org/W2916079228","https://openalex.org/W3126466933","https://openalex.org/W3133735442","https://openalex.org/W3197013133","https://openalex.org/W4214854086","https://openalex.org/W4214909616","https://openalex.org/W4233762729","https://openalex.org/W4290973502","https://openalex.org/W4296913260","https://openalex.org/W4297964528","https://openalex.org/W4317794926","https://openalex.org/W4360584595","https://openalex.org/W4380078504","https://openalex.org/W4380303648","https://openalex.org/W4383112908","https://openalex.org/W4384158362","https://openalex.org/W4386280821","https://openalex.org/W4386281092","https://openalex.org/W4387789490","https://openalex.org/W4389082198","https://openalex.org/W4389371473","https://openalex.org/W4389880061","https://openalex.org/W4391250505","https://openalex.org/W4391853601","https://openalex.org/W4393139795","https://openalex.org/W4393305293","https://openalex.org/W4396754388","https://openalex.org/W4399485132","https://openalex.org/W4401325816","https://openalex.org/W4401328436","https://openalex.org/W4401387030","https://openalex.org/W4401567990","https://openalex.org/W4403279505","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Digital":[0],"twin":[1],"(DT)-driven":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"has":[6],"emerged":[7],"as":[8],"a":[9,46,68,116,132],"promising":[10],"paradigm":[11],"for":[12,22,49,99,153,174,232],"wireless":[13,93,155],"network":[14,94,156],"optimization,":[15],"offering":[16],"safe":[17],"and":[18,89,122,201,211,228],"efficient":[19],"training":[20],"environment":[21],"policy":[23],"exploration.":[24],"However,":[25],"in":[26,85,109,128,171],"theory":[27],"existing":[28],"methods":[29],"cannot":[30],"always":[31,194],"guarantee":[32],"real-world":[33,92,111],"performance":[34,107,230],"of":[35,45,105,119,150,163,168,215],"DT-trained":[36,101],"policies":[37],"before":[38],"actual":[39],"deployment,":[40],"due":[41],"to":[42,53,76,144,159,196],"the":[43,63,73,78,87,90,103,110,120,126,129,137,146,161,169,175,191,197,204,207,212,226],"absence":[44],"universal":[47],"metric":[48,66,70],"assessing":[50],"DT\u2019s":[51],"ability":[52],"support":[54],"reliable":[55],"RL":[56],"training.":[57],"In":[58],"this":[59,221],"paper,":[60],"we":[61,178],"propose":[62,179],"DT":[64,88],"bisimulation":[65],"(DT-BSM),":[67],"novel":[69],"based":[71,135,184],"on":[72,136,185,225],"Wasserstein":[74,151],"distance,":[75],"quantify":[77],"discrepancy":[79],"between":[80,206],"Markov":[81],"decision":[82],"processes":[83],"(MDPs)":[84],"both":[86],"corresponding":[91],"environment.":[95],"We":[96,188],"prove":[97,189],"that":[98,190],"any":[100],"policy,":[102],"sub-optimality":[104,124],"its":[106,123],"(regret)":[108],"deployment":[112],"is":[113,141],"bounded":[114],"by":[115],"weighted":[117],"sum":[118],"DT-BSM":[121,134,176,182,193],"within":[125],"MDP":[127,170],"DT.":[130],"Then,":[131],"modified":[133],"total":[138],"variation":[139],"distance":[140,152],"also":[142],"introduced":[143],"avoid":[145],"prohibitive":[147],"calculation":[148],"complexity":[149],"large-scale":[154],"scenarios.":[157],"Further,":[158],"tackle":[160],"challenge":[162],"obtaining":[164],"accurate":[165],"transition":[166],"probabilities":[167],"real":[172],"world":[173],"calculation,":[177],"an":[180],"empirical":[181,192],"method":[183],"statistical":[186],"sampling.":[187],"converges":[195],"desired":[198],"theoretical":[199,223],"one,":[200],"quantitatively":[202],"establish":[203],"relationship":[205],"required":[208],"sample":[209],"size":[210],"target":[213],"level":[214],"approximation":[216],"accuracy.":[217],"Numerical":[218],"experiments":[219],"validate":[220],"first":[222],"finding":[224],"provable":[227],"calculable":[229],"bounds":[231],"DT-driven":[233],"RL.":[234]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-23T00:00:00"}