{"id":"https://openalex.org/W7117927406","doi":"https://doi.org/10.1109/milcom64451.2025.11309864","title":"GNN-Enabled Reinforcement Learning for Robust Task Admission and Routing in IoBT Environments","display_name":"GNN-Enabled Reinforcement Learning for Robust Task Admission and Routing in IoBT Environments","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W7117927406","doi":"https://doi.org/10.1109/milcom64451.2025.11309864"},"language":null,"primary_location":{"id":"doi:10.1109/milcom64451.2025.11309864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom64451.2025.11309864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2025 - 2025 IEEE Military Communications Conference (MILCOM)","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/A5042121560","display_name":"Athanasios Gkelias","orcid":"https://orcid.org/0000-0003-2121-2435"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Athanasios Gkelias","raw_affiliation_strings":["Imperial College London,EEE Department,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,EEE Department,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917506","display_name":"Kin K. Leung","orcid":"https://orcid.org/0000-0002-3860-6257"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kin K. Leung","raw_affiliation_strings":["Imperial College London,EEE Department,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,EEE Department,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085092796","display_name":"Patrick J. Baker","orcid":"https://orcid.org/0000-0002-6560-7124"},"institutions":[{"id":"https://openalex.org/I2800289278","display_name":"Royal Air Force College Cranwell","ror":"https://ror.org/01g0pjd14","country_code":"GB","type":"education","lineage":["https://openalex.org/I2800289278"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick J. Baker","raw_affiliation_strings":["Royal Air Force,Rapid Capabilities Office,Farnborough,UK"],"affiliations":[{"raw_affiliation_string":"Royal Air Force,Rapid Capabilities Office,Farnborough,UK","institution_ids":["https://openalex.org/I2800289278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041895973","display_name":"Olwen Worthington","orcid":null},"institutions":[{"id":"https://openalex.org/I1339065421","display_name":"Defence Science and Technology Laboratory","ror":"https://ror.org/04jswqb94","country_code":"GB","type":"government","lineage":["https://openalex.org/I1306956679","https://openalex.org/I1339065421","https://openalex.org/I2802373619"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olwen Worthington","raw_affiliation_strings":["Cyber & Information Systems,DSTL,Porton Down,UK"],"affiliations":[{"raw_affiliation_string":"Cyber & Information Systems,DSTL,Porton Down,UK","institution_ids":["https://openalex.org/I1339065421"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042121560"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.704291,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.6251999735832214,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.6251999735832214,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.1251000016927719,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.026900000870227814,"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":0.635200023651123},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.4154999852180481},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3799000084400177},{"id":"https://openalex.org/keywords/dynamic-network-analysis","display_name":"Dynamic network analysis","score":0.3720000088214874},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.37059998512268066},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3702000081539154},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3698999881744385},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.35339999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700999975204468},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.35339999198913574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C94600068","wikidata":"https://www.wikidata.org/wiki/Q7371621","display_name":"Routing domain","level":5,"score":0.271699994802475},{"id":"https://openalex.org/C204948658","wikidata":"https://www.wikidata.org/wiki/Q1119410","display_name":"Static routing","level":4,"score":0.2702000141143799},{"id":"https://openalex.org/C76522221","wikidata":"https://www.wikidata.org/wiki/Q5035396","display_name":"Multipath routing","level":5,"score":0.26910001039505005},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C114809511","wikidata":"https://www.wikidata.org/wiki/Q1412924","display_name":"Flow network","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom64451.2025.11309864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom64451.2025.11309864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2025 - 2025 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3188522200","https://openalex.org/W4361029956","https://openalex.org/W4376480629","https://openalex.org/W4383752013","https://openalex.org/W4390827912"],"related_works":[],"abstract_inverted_index":{"Internet":[0],"of":[1,32,182],"Battlespace":[2],"Things":[3],"(IoBT)":[4],"deployments":[5],"in":[6,12,78],"adversarial":[7],"environments":[8],"face":[9],"critical":[10],"challenges":[11],"network":[13,36,91,123,151],"resource":[14],"management,":[15],"where":[16,35],"rapid":[17],"environmental":[18],"changes":[19],"and":[20,75,108,141,202],"dynamic":[21,79,209],"threats":[22],"render":[23],"traditional":[24],"optimization":[25,49,77,124],"approaches":[26],"inadequate.":[27],"The":[28,120,184],"inherently":[29],"volatile":[30],"nature":[31],"these":[33],"environments,":[34],"conditions":[37,210],"can":[38],"change":[39],"within":[40],"seconds,":[41],"necessitates":[42],"algorithms":[43],"that":[44,112,133,154,179],"prioritize":[45],"speed":[46],"over":[47],"perfect":[48],"to":[50,143,174,199],"maintain":[51],"operational":[52],"effectiveness.":[53],"This":[54],"paper":[55],"presents":[56],"a":[57,126],"novel":[58],"Graph":[59,85],"Neural":[60],"Network":[61],"(GNN)":[62],"based":[63],"Deep":[64,94,156],"Reinforcement":[65],"Learning":[66],"(DRL)":[67],"framework":[68,185],"specifically":[69],"designed":[70],"for":[71,89,97,104],"combinatorial":[72],"task":[73,99,135,195],"admission":[74],"routing":[76,118],"IoBT":[80],"networks.":[81],"Our":[82],"approach":[83],"integrates":[84],"Attention":[86],"Networks":[87],"(GATs)":[88],"capturing":[90],"topology":[92,144],"dependencies,":[93],"Sets":[95],"encoders":[96,111],"permutation-invariant":[98],"processing,":[100],"Adaptive":[101],"Path":[102],"GNNs":[103],"learning":[105],"path":[106],"representations,":[107],"statistical":[109],"feature":[110],"complement":[113],"learned":[114],"embeddings":[115],"with":[116,169,190],"interpretable":[117],"heuristics.":[119],"system":[121],"formulates":[122],"as":[125],"Markov":[127],"Decision":[128],"Process,":[129],"enabling":[130],"real-time":[131],"decision-making":[132],"maximizes":[134],"utility":[136,168],"while":[137],"respecting":[138],"capacity":[139],"constraints":[140],"adapting":[142],"changes.":[145],"Comprehensive":[146],"experimental":[147],"evaluation":[148],"across":[149],"multiple":[150],"scenarios":[152],"demonstrates":[153],"our":[155],"Q-Network":[157],"(DQN)":[158],"agent":[159],"consistently":[160],"outperforms":[161],"greedy":[162],"baselines":[163],"by":[164],"5-58%,":[165],"achieving":[166],"near-optimal":[167],"sub-second":[170],"inference":[171],"times":[172],"compared":[173],"Mixed":[175],"Integer":[176],"Programming":[177],"solvers":[178],"require":[180],"hundreds":[181],"seconds.":[183],"shows":[186],"strong":[187],"generalization":[188],"capabilities,":[189],"agents":[191],"trained":[192,207],"on":[193],"smaller":[194],"sets":[196],"effectively":[197],"scaling":[198],"larger":[200],"workloads,":[201],"exhibits":[203],"superior":[204],"performance":[205],"when":[206],"under":[208],"rather":[211],"than":[212],"static":[213],"environments.":[214]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-01T00:00:00"}