{"id":"https://openalex.org/W3203021620","doi":"https://doi.org/10.1145/3467707.3467766","title":"Soft Actor-Critic Deep Reinforcement Learning Based Interference Resource Allocation","display_name":"Soft Actor-Critic Deep Reinforcement Learning Based Interference Resource Allocation","publication_year":2021,"publication_date":"2021-04-23","ids":{"openalex":"https://openalex.org/W3203021620","doi":"https://doi.org/10.1145/3467707.3467766","mag":"3203021620"},"language":"en","primary_location":{"id":"doi:10.1145/3467707.3467766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3467707.3467766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Computing and Artificial Intelligence","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/A5014451490","display_name":"Ning Rao","orcid":"https://orcid.org/0000-0003-3801-4187"},"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":true,"raw_author_name":"Ning Rao","raw_affiliation_strings":["Air Force Engineering University, China"],"affiliations":[{"raw_affiliation_string":"Air Force Engineering University, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413116","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-6040-3544"},"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":"Hua Xu","raw_affiliation_strings":["Air Force Engineering University, China"],"affiliations":[{"raw_affiliation_string":"Air Force Engineering University, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040753769","display_name":"Balin Song","orcid":null},"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":"Balin Song","raw_affiliation_strings":["Air Force Engineering University, China"],"affiliations":[{"raw_affiliation_string":"Air Force Engineering University, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002132866","display_name":"Yunhao Shi","orcid":"https://orcid.org/0000-0003-3493-5448"},"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":"Yunhao Shi","raw_affiliation_strings":["Air Force Engineering University, China"],"affiliations":[{"raw_affiliation_string":"Air Force Engineering University, China","institution_ids":["https://openalex.org/I4210104252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014451490"],"corresponding_institution_ids":["https://openalex.org/I4210104252"],"apc_list":null,"apc_paid":null,"fwci":0.1373,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45392761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9818999767303467,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.9735999703407288,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8346776366233826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628976106643677},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6588842868804932},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6398448348045349},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.575591504573822},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5512508153915405},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.5052648186683655},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.49167829751968384},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4913720190525055},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.4851427972316742},{"id":"https://openalex.org/keywords/jamming","display_name":"Jamming","score":0.45320868492126465},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4375247061252594},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4174790382385254},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3680068254470825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32150328159332275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16402509808540344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13478991389274597},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10601162910461426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08311590552330017}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8346776366233826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628976106643677},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6588842868804932},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6398448348045349},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.575591504573822},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5512508153915405},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.5052648186683655},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49167829751968384},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4913720190525055},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.4851427972316742},{"id":"https://openalex.org/C2779079576","wikidata":"https://www.wikidata.org/wiki/Q17092823","display_name":"Jamming","level":2,"score":0.45320868492126465},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4375247061252594},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4174790382385254},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3680068254470825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32150328159332275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16402509808540344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13478991389274597},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10601162910461426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08311590552330017},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3467707.3467766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3467707.3467766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Computing and Artificial Intelligence","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":12,"referenced_works":["https://openalex.org/W1534441433","https://openalex.org/W1583837637","https://openalex.org/W2079669620","https://openalex.org/W2266687685","https://openalex.org/W2320144636","https://openalex.org/W2333032143","https://openalex.org/W2524142004","https://openalex.org/W2529741607","https://openalex.org/W2777240447","https://openalex.org/W2785681039","https://openalex.org/W2962983127","https://openalex.org/W3032998286"],"related_works":["https://openalex.org/W2378749186","https://openalex.org/W2364088131","https://openalex.org/W4200319726","https://openalex.org/W2362741838","https://openalex.org/W1984793747","https://openalex.org/W622044715","https://openalex.org/W4312547492","https://openalex.org/W3197729047","https://openalex.org/W1624160917","https://openalex.org/W2167858308"],"abstract_inverted_index":{"For":[0],"the":[1,13,20,48,74,78,85,91,98,108,114],"future":[2],"information":[3,102],"countermeasure,":[4],"a":[5,60],"single":[6],"interference":[7,34],"mode":[8],"is":[9,27,111],"not":[10],"effective":[11],"as":[12,52],"electromagnetic":[14],"environment":[15],"becomes":[16],"increasingly":[17],"complex.":[18],"Under":[19],"condition":[21],"of":[22,100],"limited":[23],"countermeasure":[24],"resources,":[25],"it":[26],"particularly":[28],"important":[29],"to":[30,38,113],"formulate":[31],"an":[32],"appropriate":[33],"resource":[35,49,67],"allocation":[36,50,68,80],"scheme":[37,81],"obtain":[39],"better":[40],"jamming":[41],"efficacy.":[42],"In":[43],"this":[44],"article,":[45],"we":[46],"model":[47],"problem":[51],"Discrete-time":[53],"Finite-state":[54],"Markov":[55],"Decision":[56],"Process":[57],"and":[58,87,119],"propose":[59],"soft":[61],"actor-critic":[62],"deep":[63],"reinforcement":[64],"learning":[65],"based":[66],"algorithm.":[69],"With":[70],"less":[71],"prior":[72],"information,":[73],"algorithm":[75,110],"can":[76],"learn":[77],"best":[79],"by":[82,95],"interacting":[83],"with":[84,97],"environment,":[86],"avoid":[88],"falling":[89],"into":[90],"local":[92],"optimal":[93],"solution":[94],"combining":[96],"maximization":[99],"policy":[101],"entropy.":[103],"Simulation":[104],"results":[105],"show":[106],"that":[107],"proposed":[109],"superior":[112],"existing":[115],"algorithms":[116],"in":[117],"stability":[118],"optimization":[120],"speed.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}