{"id":"https://openalex.org/W4417130966","doi":"https://doi.org/10.1109/lra.2025.3641098","title":"Supervision-Enhanced Deep Reinforcement Learning for Hybrid Action in BVR Engagement","display_name":"Supervision-Enhanced Deep Reinforcement Learning for Hybrid Action in BVR Engagement","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417130966","doi":"https://doi.org/10.1109/lra.2025.3641098"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3641098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3641098","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation 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/A5040472114","display_name":"Haoran Han","orcid":"https://orcid.org/0000-0002-0728-3993"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Han","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0728-3993","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039059630","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0001-6966-0531"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6966-0531","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684874","display_name":"Maolong Lv","orcid":"https://orcid.org/0000-0001-6406-2399"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maolong Lv","raw_affiliation_strings":["Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-6406-2399","affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051993850","display_name":"Li Mo","orcid":"https://orcid.org/0000-0001-6467-896X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Mo","raw_affiliation_strings":["School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6467-896X","affiliations":[{"raw_affiliation_string":"School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6622,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97248368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"11","issue":"2","first_page":"1138","last_page":"1145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T12158","display_name":"Guidance and Control Systems","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T13371","display_name":"Military Defense Systems Analysis","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7892000079154968},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/missile","display_name":"Missile","score":0.5425999760627747},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.44269999861717224},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4422999918460846}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7892000079154968},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C2778857364","wikidata":"https://www.wikidata.org/wiki/Q974850","display_name":"Missile","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5267999768257141},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.4307999908924103},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C2777790407","wikidata":"https://www.wikidata.org/wiki/Q383695","display_name":"Flight training","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3641098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3641098","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3440229076","display_name":null,"funder_award_id":"62303489","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3934599601","display_name":null,"funder_award_id":"GKJJ24050502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6087676565","display_name":null,"funder_award_id":"U2233209","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2951360122","https://openalex.org/W3112673853","https://openalex.org/W4309483453","https://openalex.org/W4312309366","https://openalex.org/W4380520220","https://openalex.org/W4384822329","https://openalex.org/W4386574907","https://openalex.org/W4394823112","https://openalex.org/W4394966964","https://openalex.org/W4399381823","https://openalex.org/W4399412621","https://openalex.org/W4406612018","https://openalex.org/W4408860750","https://openalex.org/W4410204461","https://openalex.org/W4410537694","https://openalex.org/W4410985752","https://openalex.org/W4411142737","https://openalex.org/W4411551029","https://openalex.org/W4411949385"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,82],"learning":[2,83,90],"has":[3],"gained":[4],"increasing":[5],"popularity":[6],"in":[7],"the":[8,20,23,44,55,58,75,81,104,113,118,125,149,152],"beyond":[9],"visual":[10],"range":[11],"engagement":[12,45],"of":[13,19,22,57,97,151],"unmanned":[14],"combat":[15],"aerial":[16],"vehicles.":[17],"Regardless":[18],"success":[21],"maneuvering":[24,72,108,135],"decision,":[25],"existing":[26],"methods":[27],"either":[28],"utilize":[29],"sparse":[30],"rewards":[31],"to":[32,53,71,77,94,133],"optimize":[33],"fire":[34,40,78,119],"control":[35,120],"or":[36],"adopt":[37],"a":[38,50],"predefined":[39],"policy,":[41],"severely":[42],"limiting":[43],"performance.":[46],"This":[47,129],"paper":[48],"presents":[49],"supervision-enhanced":[51],"technique":[52],"address":[54],"challenges":[56],"hybrid":[59],"action":[60],"space.":[61],"A":[62],"dual-head":[63],"policy":[64,115],"is":[65,92,110,122],"developed,":[66],"with":[67,112,124],"one":[68],"head":[69,109,121],"dedicated":[70],"decisions":[73,136],"and":[74,103,137],"other":[76],"control.":[79],"Alongside":[80],"memory":[84,91],"that":[85],"stores":[86],"state":[87],"transitions,":[88],"supervised":[89],"introduced":[93],"store":[95],"pairs":[96],"states":[98],"where":[99],"missiles":[100],"are":[101],"launched":[102],"hit":[105,140],"outcomes.":[106],"The":[107],"trained":[111],"soft":[114],"gradient,":[116],"while":[117],"optimized":[123],"binary":[126],"cross-entropy":[127],"loss.":[128],"method":[130],"enables":[131],"agents":[132],"make":[134],"predict":[138],"missile":[139],"probabilities":[141],"simultaneously":[142],"without":[143],"prior":[144],"expert":[145],"knowledge.":[146],"Simulation":[147],"demonstrates":[148],"superiority":[150],"proposed":[153],"method.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-12-08T00:00:00"}