{"id":"https://openalex.org/W4417471407","doi":"https://doi.org/10.1109/lwc.2025.3642168","title":"Reinforcement Learning-Based Policy Optimization for Heterogeneous Radio Access","display_name":"Reinforcement Learning-Based Policy Optimization for Heterogeneous Radio Access","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W4417471407","doi":"https://doi.org/10.1109/lwc.2025.3642168"},"language":"en","primary_location":{"id":"doi:10.1109/lwc.2025.3642168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2025.3642168","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications 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/A5088283583","display_name":"Anup Mishra","orcid":"https://orcid.org/0000-0003-1544-5363"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anup Mishra","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-1544-5363","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054388477","display_name":"\u010cedomir Stefanovi\u0107","orcid":"https://orcid.org/0000-0002-9361-2908"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"\u010cedomir Stefanovi\u0107","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-9361-2908","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071289803","display_name":"Petar Popovski","orcid":"https://orcid.org/0000-0001-6195-4797"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Petar Popovski","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6195-4797","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061754527","display_name":"Israel Leyva\u2010Mayorga","orcid":"https://orcid.org/0000-0002-7116-397X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Israel Leyva-Mayorga","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-7116-397X","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3447016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"1050","last_page":"1054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12079","display_name":"IoT Networks and Protocols","score":0.4993000030517578,"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/T12079","display_name":"IoT Networks and Protocols","score":0.4993000030517578,"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/T11158","display_name":"Wireless Networks and Protocols","score":0.2248000055551529,"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":0.11739999800920486,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6531000137329102},{"id":"https://openalex.org/keywords/aloha","display_name":"Aloha","score":0.585099995136261},{"id":"https://openalex.org/keywords/telecommunications-link","display_name":"Telecommunications link","score":0.5435000061988831},{"id":"https://openalex.org/keywords/base-station","display_name":"Base station","score":0.5339000225067139},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5331000089645386},{"id":"https://openalex.org/keywords/radio-access-network","display_name":"Radio access network","score":0.451200008392334},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4375999867916107},{"id":"https://openalex.org/keywords/user-equipment","display_name":"User equipment","score":0.4090000092983246},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.3937000036239624},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360000252723694},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6531000137329102},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.6233000159263611},{"id":"https://openalex.org/C2776398200","wikidata":"https://www.wikidata.org/wiki/Q508880","display_name":"Aloha","level":4,"score":0.585099995136261},{"id":"https://openalex.org/C138660444","wikidata":"https://www.wikidata.org/wiki/Q5607897","display_name":"Telecommunications link","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.484499990940094},{"id":"https://openalex.org/C106365562","wikidata":"https://www.wikidata.org/wiki/Q3078360","display_name":"Radio access network","level":4,"score":0.451200008392334},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C2781327853","wikidata":"https://www.wikidata.org/wiki/Q3552547","display_name":"User equipment","level":3,"score":0.4090000092983246},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3937000036239624},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C509933004","wikidata":"https://www.wikidata.org/wiki/Q194163","display_name":"Broadband","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2779765720","wikidata":"https://www.wikidata.org/wiki/Q5005908","display_name":"C-RAN","level":5,"score":0.3181000053882599},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C56685638","wikidata":"https://www.wikidata.org/wiki/Q2300474","display_name":"Power control","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2780137118","wikidata":"https://www.wikidata.org/wiki/Q17121585","display_name":"Radio access technology","level":4,"score":0.2939999997615814},{"id":"https://openalex.org/C125599584","wikidata":"https://www.wikidata.org/wiki/Q15057100","display_name":"Broadband networks","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C78834623","wikidata":"https://www.wikidata.org/wiki/Q640394","display_name":"Mobile broadband","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C62793504","wikidata":"https://www.wikidata.org/wiki/Q228327","display_name":"Access network","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C182448111","wikidata":"https://www.wikidata.org/wiki/Q7281197","display_name":"Radio resource management","level":4,"score":0.25780001282691956},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lwc.2025.3642168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2025.3642168","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications Letters","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/b6fe1d3d-8b8a-4062-a7d8-c28889d43af0","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/b6fe1d3d-8b8a-4062-a7d8-c28889d43af0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mishra, A, Stefanovi\u0107, \u010c, Popovski, P & Leyva-Mayorga, I 2026, 'Reinforcement Learning-Based Policy Optimization for Heterogeneous Radio Access', IEEE Wireless Communications Letters, vol. 15, 11303578, pp. 1050-1054. https://doi.org/10.1109/LWC.2025.3642168","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Heterogeneous":[0],"services":[1,36],"such":[2],"as":[3,170],"broadband":[4,153,218],"and":[5,32,63,105,188,196,220,228],"latency-constrained":[6,158],"internet-of-things":[7],"(IoT),":[8],"with":[9,156],"diverse":[10],"requirements,":[11],"make":[12],"efficient":[13],"resource":[14],"sharing":[15],"challenging.":[16],"Two":[17],"canonical":[18],"strategies":[19,182],"are":[20],"radio":[21],"access":[22,47,167],"network":[23],"(RAN)":[24],"Slicing,":[25],"which":[26],"allocates":[27],"disjoint":[28],"resources":[29],"per":[30],"service,":[31],"RAN":[33,194,197],"Sharing,":[34],"where":[35,125,151],"coexist":[37],"on":[38,68,87],"a":[39,49,152,171],"common":[40],"resource.":[41],"Under":[42,192],"either":[43],"regime,":[44],"grant-free":[45,162],"repetition-based":[46],"is":[48],"key":[50],"enabler":[51],"of":[52],"IoT":[53,127,159,166,213],"connectivity":[54],"prompting":[55],"latency-aware":[56],"policies":[57],"tuned":[58],"to":[59,101,133,178],"the":[60,108,200,225],"regimes\u2019":[61],"density":[62],"interference":[64],"profiles.":[65],"Prior":[66],"work":[67],"repetition-policy":[69],"optimisation":[70,169],"mainly":[71],"employs":[72],"base":[73],"station":[74],"(BS)-centric":[75],"reinforcement":[76],"learning":[77],"(RL)":[78],"or":[79],"irregular":[80],"repetition":[81],"slotted":[82],"ALOHA":[83],"(IRSA)-based":[84],"approaches":[85],"focused":[86],"throughput/packet":[88],"loss":[89],"rate":[90],"(PLR)":[91],"in":[92,137,207],"asymptotic":[93],"regimes.":[94],"The":[95],"former":[96],"requires":[97],"central":[98],"orchestration,":[99],"leading":[100],"high":[102],"control":[103],"overhead":[104],"reduced":[106],"adaptability;":[107],"latter":[109],"typically":[110],"degrades":[111],"when":[112],"targeting":[113],"performance":[114],"at":[115],"finite":[116,139,184],"frame":[117,185],"lengths.":[118],"This":[119],"motivates":[120],"decentralised":[121,205],"multi-agent":[122],"RL":[123],"(MARL),":[124],"each":[126,208],"device":[128],"learns":[129],"its":[130],"own":[131],"policy":[132,168],"meet":[134],"latency":[135,190,214],"targets":[136],"dense,":[138],"frame-length,":[140],"mixed-service":[141],"deployments.":[142],"To":[143],"this":[144],"end,":[145],"we":[146],"investigate":[147],"an":[148],"uplink":[149],"scenario":[150],"user":[154],"coexists":[155],"multiple":[157],"devices":[160,177],"employing":[161],"access.":[163],"We":[164],"formulate":[165],"decentralised,":[172],"model-free":[173],"MARL":[174],"problem,":[175],"enabling":[176],"learn":[179],"their":[180],"transmission":[181],"under":[183],"length":[186],"structures":[187],"strict":[189],"requirements.":[191],"both":[193],"Slicing":[195],"Sharing":[198],"regimes,":[199],"proposed":[201],"scheme":[202],"outperforms":[203],"baseline":[204],"approaches;":[206],"regime":[209],"it":[210],"achieves":[211],"substantial":[212],"gains":[215],"while":[216],"sustaining":[217],"throughput":[219],"energy":[221],"efficiency":[222],"(EE).":[223],"Furthermore,":[224],"results":[226],"highlight":[227],"compare":[229],"regime-specific":[230],"trade-offs.":[231]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-18T00:00:00"}
