{"id":"https://openalex.org/W7133252658","doi":"https://doi.org/10.1109/jsac.2026.3669465","title":"Self-Attention Proximal Policy Optimization for Beam Tracking in mmWave Communications","display_name":"Self-Attention Proximal Policy Optimization for Beam Tracking in mmWave Communications","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133252658","doi":"https://doi.org/10.1109/jsac.2026.3669465"},"language":null,"primary_location":{"id":"doi:10.1109/jsac.2026.3669465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2026.3669465","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","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/A5127781789","display_name":"Xin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4687-076X","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Tan","orcid":"https://orcid.org/0000-0003-1868-0123"},"institutions":[{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":["Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1868-0123","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127871889","display_name":"Xiaoguang Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Ren","raw_affiliation_strings":["Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127823692","display_name":"Huadong Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huadong Dai","raw_affiliation_strings":["Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9722-5454","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory (IGDL), Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210161752"],"apc_list":null,"apc_paid":null,"fwci":4.828,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92949091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"44","issue":null,"first_page":"4552","last_page":"4569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.5939000248908997,"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/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.5939000248908997,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.13259999454021454,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.04659999907016754,"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/tracking","display_name":"Tracking (education)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5931000113487244},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5367000102996826},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.48069998621940613},{"id":"https://openalex.org/keywords/beam","display_name":"Beam (structure)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4196000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278999924659729},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.48069998621940613},{"id":"https://openalex.org/C168834538","wikidata":"https://www.wikidata.org/wiki/Q3705329","display_name":"Beam (structure)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C148063708","wikidata":"https://www.wikidata.org/wiki/Q5072511","display_name":"Channel state information","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jsac.2026.3669465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2026.3669465","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3169641002","display_name":null,"funder_award_id":"62402499","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Millimeter-wave":[0],"(mmWave)":[1],"communication":[2],"systems":[3],"are":[4],"highly":[5],"sensitive":[6],"to":[7,29,71],"user":[8,118],"mobility":[9,135],"and":[10,20,37,80,120,136,155,163,188],"environmental":[11],"changes,":[12],"often":[13],"suffering":[14],"from":[15],"rapid":[16],"beam":[17,32,39,54,178],"direction":[18],"shifts":[19],"frequent":[21,170],"link":[22],"blockages.":[23],"These":[24],"dynamics":[25],"pose":[26],"significant":[27],"challenges":[28],"maintaining":[30],"reliable":[31,189],"tracking.":[33],"To":[34,124],"enable":[35],"accurate":[36],"robust":[38],"tracking":[40,55,160,179],"in":[41,157,166],"dynamic":[42,192],"environments,":[43],"we":[44,128],"propose":[45],"a":[46,60,95,101,177],"Self-Attention":[47],"Proximal":[48],"Policy":[49],"Optimization":[50],"(SAPPO)":[51],"algorithm.":[52],"The":[53],"task":[56],"is":[57],"modeled":[58],"as":[59,153],"Partially":[61],"Observable":[62],"Markov":[63],"Decision":[64],"Process":[65],"(POMDP),":[66],"where":[67],"the":[68,106,114,126,140],"agent":[69],"aims":[70],"maximize":[72],"Received":[73],"Signal":[74],"Strength":[75],"(RSS)":[76],"using":[77,139],"only":[78],"current":[79],"previous":[81],"signal":[82,91],"observations,":[83],"without":[84],"relying":[85],"on":[86],"channel":[87,121],"models":[88],"or":[89],"complex":[90],"processing.":[92],"By":[93],"integrating":[94],"multi-head":[96],"self-attention":[97],"(MHSA)":[98],"mechanism":[99],"with":[100,133,169],"Gated":[102],"Recurrent":[103],"Unit":[104],"(GRU),":[105],"policy":[107],"network":[108],"effectively":[109],"captures":[110],"temporal":[111],"dependencies,":[112],"enhancing":[113],"agent\u2019s":[115],"perception":[116],"of":[117,159],"motion":[119],"state":[122],"variations.":[123],"validate":[125],"approach,":[127],"construct":[129],"three":[130],"test":[131],"scenarios":[132],"varying":[134],"blockage":[137],"complexity":[138],"DeepMIMO":[141],"dataset.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"that":[146],"SAPPO":[147,175],"consistently":[148],"outperforms":[149],"baseline":[150],"methods":[151],"such":[152],"DQN":[154],"PPO":[156],"terms":[158],"accuracy,":[161],"stability,":[162],"robustness.":[164],"Notably,":[165],"challenging":[167],"environments":[168],"Line-Of-Sight":[171],"(LOS)/Non-Line-Of-Sight":[172],"(NLOS)":[173],"transitions,":[174],"achieves":[176],"success":[180],"rate":[181],"exceeding":[182],"95%,":[183],"highlighting":[184],"its":[185],"strong":[186],"adaptability":[187],"performance":[190],"under":[191],"conditions.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-22T06:01:30.510260","created_date":"2026-03-03T00:00:00"}