{"id":"https://openalex.org/W4403331804","doi":"https://doi.org/10.23919/fusion59988.2024.10706358","title":"A Deep Reinforcement Learning-Based Whittle Index Policy for Multibeam Allocation","display_name":"A Deep Reinforcement Learning-Based Whittle Index Policy for Multibeam Allocation","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4403331804","doi":"https://doi.org/10.23919/fusion59988.2024.10706358"},"language":"en","primary_location":{"id":"doi:10.23919/fusion59988.2024.10706358","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fusion59988.2024.10706358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Information Fusion (FUSION)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004478315","display_name":"Yuhang Hao","orcid":"https://orcid.org/0000-0002-3319-4206"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Hao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034492629","display_name":"Jing Fu","orcid":"https://orcid.org/0000-0003-4615-8391"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Fu","raw_affiliation_strings":["Royal Melbourne Institute of Technology University,School of Engineering,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Melbourne Institute of Technology University,School of Engineering,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110620243","display_name":"Quan Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Pan","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5184999704360962,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5184999704360962,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.4871000051498413,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8631061315536499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6580392122268677},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5670363306999207},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44427961111068726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43196603655815125},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3299649953842163},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1764375865459442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1433289647102356},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09732720255851746},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0862603485584259}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8631061315536499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6580392122268677},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5670363306999207},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44427961111068726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43196603655815125},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3299649953842163},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1764375865459442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1433289647102356},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09732720255851746},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0862603485584259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/fusion59988.2024.10706358","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fusion59988.2024.10706358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Information Fusion (FUSION)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":25,"referenced_works":["https://openalex.org/W2056921512","https://openalex.org/W2072566913","https://openalex.org/W2105266096","https://openalex.org/W2491264664","https://openalex.org/W2911767333","https://openalex.org/W2914304175","https://openalex.org/W2947022728","https://openalex.org/W2955184042","https://openalex.org/W2980173049","https://openalex.org/W2999111912","https://openalex.org/W3002855444","https://openalex.org/W3007664534","https://openalex.org/W3043858839","https://openalex.org/W3113208582","https://openalex.org/W3172390835","https://openalex.org/W4206562833","https://openalex.org/W4238559453","https://openalex.org/W4285031101","https://openalex.org/W4294310995","https://openalex.org/W4295252942","https://openalex.org/W4389768159","https://openalex.org/W6687367344","https://openalex.org/W6791428249","https://openalex.org/W6859326365","https://openalex.org/W6959740464"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,15,88,150],"non-myopic":[4],"beam":[5,168],"scheduling":[6],"policy":[7,39,144,219],"is":[8,101,106,128],"proposed":[9,217],"for":[10,87,171],"multi-target":[11],"tracking":[12,26,34,67,153],"(MTT)":[13],"in":[14,98,147,203],"phased-array":[16],"radar":[17],"network,":[18],"seeking":[19],"to":[20,108,130,165],"minimize":[21],"the":[22,32,42,50,54,66,73,83,91,95,110,118,132,137,141,157,167,181,191,204,213,216],"discounted":[23],"sum":[24],"of":[25,28,53,75,94,113,140,185,207,215,222],"error":[27,68],"targets":[29],"and":[30,116,145,190,200,225],"improve":[31],"long-term":[33],"performance.":[35],"The":[36,103,122],"Whittle":[37,96,120,142,159],"index":[38,97,143,160],"based":[40,81],"on":[41,82],"restless":[43],"multiarmed":[44],"bandit":[45],"(RMAB)":[46],"model":[47],"can":[48],"decompose":[49],"state":[51,74,199],"space":[52],"underlying":[55],"optimization":[56],"problem":[57,170],"into":[58],"independent":[59],"spaces":[60,202],"with":[61,149,173],"reduced":[62],"sizes.":[63],"We":[64,155],"consider":[65],"covariance":[69],"(TEC)":[70],"matrix":[71],"as":[72],"each":[76],"target":[77,152],"(arm),":[78],"which":[79],"evolves":[80],"Kalman":[84],"filter.":[85],"However,":[86],"real-world":[89],"MTT,":[90],"exact":[92],"calculation":[93],"multiple":[99],"dimensions":[100],"challenging.":[102],"neural":[104,133],"network":[105,134],"established":[107],"achieve":[109],"feature":[111],"extraction":[112],"TEC":[114,175],"states":[115],"learn":[117],"corresponding":[119],"index.":[121],"deep":[123],"reinforcement":[124],"learning":[125],"(DRL)":[126],"method":[127],"exploited":[129],"train":[131],"by":[135,196],"leveraging":[136],"threshold":[138],"property":[139],"engaging":[146],"interactions":[148],"single":[151],"environment.":[154],"propose":[156],"DRL-based":[158],"policy,":[161],"namely":[162],"DRLWI,":[163],"aiming":[164],"solve":[166],"allocation":[169],"MTT":[172],"multi-dimensional":[174],"states.":[176],"This":[177],"approach":[178],"effectively":[179],"mitigates":[180],"exponential":[182],"computational":[183],"complexity":[184],"classical":[186],"dynamic":[187],"programming":[188],"approaches":[189],"low":[192],"convergence":[193],"rate":[194],"caused":[195],"large":[197],"joint":[198],"action":[201],"simple":[205],"application":[206],"DRL":[208,223],"algorithms.":[209],"Numerical":[210],"results":[211],"demonstrate":[212],"performance":[214],"DRLWI":[218],"surpasses":[220],"that":[221],"algorithms":[224],"myopic":[226],"policies.":[227]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}