{"id":"https://openalex.org/W7162289181","doi":"https://doi.org/10.1109/tccn.2026.3696628","title":"Knowledge-Guided Deep Reinforcement Learning for Timely State Estimation in Wireless Embodied Networks","display_name":"Knowledge-Guided Deep Reinforcement Learning for Timely State Estimation in Wireless Embodied Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162289181","doi":"https://doi.org/10.1109/tccn.2026.3696628"},"language":null,"primary_location":{"id":"doi:10.1109/tccn.2026.3696628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tccn.2026.3696628","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"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 Cognitive Communications and Networking","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/A5079654233","display_name":"J C Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazheng Chen","raw_affiliation_strings":["School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2439-0800","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079772530","display_name":"Changyang She","orcid":"https://orcid.org/0000-0003-0193-9784"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyang She","raw_affiliation_strings":["School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0193-9784","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104044154","display_name":"Zheng Ping","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128865","display_name":"China GreatWall Technology Group (China)","ror":"https://ror.org/02t3qgb38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128865"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zheng","raw_affiliation_strings":["China Greatwall Technology Group Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Greatwall Technology Group Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210128865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052021760","display_name":"B Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohai Li","raw_affiliation_strings":["School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7000-8129","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136930190","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52212992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"8522","last_page":"8535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13279999792575836,"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":0.13279999792575836,"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/T13553","display_name":"Age of Information Optimization","score":0.13040000200271606,"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/T12216","display_name":"Network Time Synchronization Technologies","score":0.057100001722574234,"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":0.6934000253677368},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.541100025177002},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.46869999170303345},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4226999878883362},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245999813079834},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6934000253677368},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.46869999170303345},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C2989466925","wikidata":"https://www.wikidata.org/wiki/Q1061197","display_name":"Radio networks","level":4,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tccn.2026.3696628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tccn.2026.3696628","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"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 Cognitive Communications and Networking","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":36,"referenced_works":["https://openalex.org/W1993411524","https://openalex.org/W2022406843","https://openalex.org/W2024509105","https://openalex.org/W2106864314","https://openalex.org/W2114004090","https://openalex.org/W2478708596","https://openalex.org/W2911087563","https://openalex.org/W2963060851","https://openalex.org/W2979881298","https://openalex.org/W2994803162","https://openalex.org/W3000486967","https://openalex.org/W3016268025","https://openalex.org/W3041911152","https://openalex.org/W3128965347","https://openalex.org/W3139933459","https://openalex.org/W3174812399","https://openalex.org/W4210402736","https://openalex.org/W4285104925","https://openalex.org/W4285203333","https://openalex.org/W4312288984","https://openalex.org/W4312766166","https://openalex.org/W4312881208","https://openalex.org/W4313053314","https://openalex.org/W4313455370","https://openalex.org/W4378195029","https://openalex.org/W4379184851","https://openalex.org/W4387883765","https://openalex.org/W4388266341","https://openalex.org/W4392207762","https://openalex.org/W4396214411","https://openalex.org/W4402774450","https://openalex.org/W4407390684","https://openalex.org/W4414110682","https://openalex.org/W4415970870","https://openalex.org/W7116890390","https://openalex.org/W7124425475"],"related_works":[],"abstract_inverted_index":{"Remote":[0],"state":[1,52],"estimation":[2,169],"of":[3,15,60,71,78,103,167],"numerous":[4],"functional":[5],"components":[6],"is":[7,121,137],"essential":[8],"for":[9,48,115],"the":[10,27,57,61,67,72,76,79,86,95,101,104,117,125,129,134,144,153,158,168,174,180],"reliable":[11],"and":[12,43,75,106,133,173],"real-time":[13],"operation":[14],"modern":[16],"embodied":[17,36],"intelligent":[18],"agents.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,55,84],"focus":[24],"on":[25,128],"solving":[26],"optimal":[28,62,73,80],"resource":[29,63],"allocation":[30,64],"problem":[31],"in":[32,165],"such":[33],"a":[34,112],"large-scale":[35],"network":[37],"with":[38],"massive":[39],"connected":[40],"sensing":[41],"devices":[42],"limited":[44],"wireless":[45],"spectrum":[46],"resources":[47],"achieving":[49],"high-quality":[50],"remote":[51],"estimation.":[53],"First,":[54],"derive":[56],"structural":[58,97],"properties":[59],"policy,":[65],"including":[66],"no-waste":[68,130],"channel":[69,131],"structure":[70],"action":[74,126],"monotonicity":[77,145],"value":[81],"function.":[82],"Next,":[83],"propose":[85],"Knowledge-Guided":[87],"deep":[88],"reinforcement":[89],"learning":[90,120],"(KG-DRL)":[91],"algorithm":[92,156],"by":[93,123,142,162,184],"leveraging":[94],"derived":[96],"knowledge":[98],"to":[99,139],"guide":[100],"training":[102],"actor":[105,118],"critic":[107,135],"neural":[108],"networks":[109],"(NNs).":[110],"Specifically,":[111],"structure-guided":[113],"trajectory":[114],"facilitating":[116],"NN":[119,136],"generated":[122],"selecting":[124],"based":[127],"structure,":[132],"guided":[138],"be":[140],"monotonic":[141],"introducing":[143],"violation":[146],"penalty":[147],"term.":[148],"Numerical":[149],"results":[150],"illustrate":[151],"that":[152],"proposed":[154],"KG-DRL":[155],"outperforms":[157],"benchmark":[159],"DRL":[160],"algorithms":[161],"about":[163],"20%-35%":[164],"terms":[166],"mean-square":[170],"error":[171],"(MSE)":[172],"total":[175],"power":[176],"consumption,":[177],"while":[178],"saving":[179],"required":[181],"convergence":[182],"episodes":[183],"approximately":[185],"35%.":[186]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-26T00:00:00"}