{"id":"https://openalex.org/W4417282364","doi":"https://doi.org/10.1109/pimrc62392.2025.11274591","title":"Practical Policy Distillation for Reinforcement Learning in Radio Access Networks","display_name":"Practical Policy Distillation for Reinforcement Learning in Radio Access Networks","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4417282364","doi":"https://doi.org/10.1109/pimrc62392.2025.11274591"},"language":null,"primary_location":{"id":"doi:10.1109/pimrc62392.2025.11274591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032707626","display_name":"Sara Khosravi","orcid":"https://orcid.org/0000-0003-0182-2877"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sara Khosravi","raw_affiliation_strings":["Ericsson AB,Kista,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson AB,Kista,Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019452377","display_name":"Burak Demirel","orcid":"https://orcid.org/0000-0003-0731-4881"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Burak Demirel","raw_affiliation_strings":["Ericsson AB,Kista,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson AB,Kista,Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linghui Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Linghui Zhou","raw_affiliation_strings":["Ericsson AB,Kista,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson AB,Kista,Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067843387","display_name":"Javier Rasines","orcid":null},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Javier Rasines","raw_affiliation_strings":["Ericsson AB,Kista,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson AB,Kista,Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028170413","display_name":"Pablo Soldati","orcid":"https://orcid.org/0000-0001-6398-6258"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Pablo Soldati","raw_affiliation_strings":["Ericsson AB,Kista,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson AB,Kista,Sweden","institution_ids":["https://openalex.org/I1306339040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306339040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49051693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.37049999833106995,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.37049999833106995,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.24449999630451202,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.03750000149011612,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7548999786376953},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5544000267982483},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5379999876022339},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45750001072883606},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45730000734329224},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42660000920295715},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/radio-access-network","display_name":"Radio access network","score":0.3310999870300293}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7548999786376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121999859809875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C106365562","wikidata":"https://www.wikidata.org/wiki/Q3078360","display_name":"Radio access network","level":4,"score":0.3310999870300293},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C65165936","wikidata":"https://www.wikidata.org/wiki/Q575784","display_name":"Baseband","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pimrc62392.2025.11274591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.48550/arxiv.2511.06563","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2511.06563","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2282548695","https://openalex.org/W2294370754","https://openalex.org/W2891171329","https://openalex.org/W2963836746","https://openalex.org/W3034368386","https://openalex.org/W3212472652","https://openalex.org/W4283760176","https://openalex.org/W4284967244","https://openalex.org/W4293192705","https://openalex.org/W4377704417","https://openalex.org/W4388108106","https://openalex.org/W4400647478"],"related_works":[],"abstract_inverted_index":{"Adopting":[0],"artificial":[1],"intelligence":[2],"(AI)":[3],"in":[4,46,56,114,158],"radio":[5],"access":[6],"networks":[7],"(RANs)":[8],"presents":[9],"several":[10],"challenges,":[11],"limited":[12],"availability":[13],"of":[14,52,117,186],"link-level":[15],"measurements":[16],"(e.g.,":[17,24],"CQI":[18],"reports),":[19],"stringent":[20],"real-time":[21],"processing":[22],"constraints":[23],"sub-1ms":[25],"per":[26],"TTI),":[27],"and":[28,36,49,75,87,142,183],"network":[29,95],"heterogeneity":[30],"(different":[31],"spectrum":[32],"bands,":[33],"cell":[34],"types,":[35],"vendor":[37],"equipment).":[38],"A":[39],"critical":[40],"yet":[41],"often":[42,97],"overlooked":[43],"barrier":[44],"lies":[45],"the":[47,115,174,181],"computational":[48,182],"memory":[50,184],"limitations":[51,185],"RAN":[53,188],"baseband":[54],"hardware\u2014particularly":[55],"legacy":[57],"4thGeneration":[58],"(4G)":[59],"systems\u2014which":[60],"typically":[61],"lack":[62],"on-chip":[63],"neural":[64],"accelerators.":[65],"As":[66],"a":[67,118,131,152,159],"result,":[68],"only":[69],"lightweight":[70],"AI":[71],"models":[72,100,171],"(under":[73],"1Mb":[74],"sub-100\u00b5s":[76],"inference":[77],"time)":[78],"can":[79],"be":[80],"effectively":[81],"deployed,":[82],"limiting":[83],"both":[84,166],"their":[85],"performance":[86],"applicability.":[88],"However,":[89],"achieving":[90],"strong":[91],"generalization":[92,176],"across":[93],"diverse":[94],"conditions":[96],"requires":[98],"large-scale":[99],"with":[101,180],"substantial":[102],"resource":[103],"demands.":[104],"To":[105],"address":[106],"this":[107,109],"trade-off,":[108],"paper":[110],"investigates":[111],"policy":[112],"distillation":[113],"context":[116],"reinforcement":[119],"learning\u2013based":[120],"link":[121],"adaptation":[122],"task.":[123],"We":[124],"explore":[125],"two":[126],"strategies:":[127],"single-policy":[128],"distillation,":[129,144],"where":[130,145],"scenario-agnostic":[132],"teacher":[133],"model":[134],"is":[135],"compressed":[136],"into":[137,151],"one":[138],"generalized":[139],"student":[140,170],"model;":[141],"multi-policy":[143],"multiple":[146],"scenario-specific":[147],"teachers":[148],"are":[149],"consolidated":[150],"single":[153],"generalist":[154],"student.":[155],"Experimental":[156],"evaluations":[157],"high-fidelity,":[160],"5thGeneration":[161],"(5G)-compliant":[162],"simulator":[163],"demonstrate":[164],"that":[165,172],"strategies":[167],"produce":[168],"compact":[169],"preserve":[173],"teachers\u2019":[175],"capabilities":[177],"while":[178],"complying":[179],"existing":[187],"hardware.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-12T00:00:00"}