{"id":"https://openalex.org/W4394840354","doi":"https://doi.org/10.1145/3650215.3650293","title":"Research on path planning algorithm of partially observable penetration test based on reinforcement learning","display_name":"Research on path planning algorithm of partially observable penetration test based on reinforcement learning","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4394840354","doi":"https://doi.org/10.1145/3650215.3650293"},"language":"en","primary_location":{"id":"doi:10.1145/3650215.3650293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650215.3650293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Conference on Machine Learning and Computer Application","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/A5091035078","display_name":"Qintao Sun","orcid":"https://orcid.org/0009-0005-0195-8178"},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinrui Sun","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering, China"],"raw_orcid":"https://orcid.org/0009-0005-0195-8178","affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering, China","institution_ids":["https://openalex.org/I2802615301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058603845","display_name":"Ge Hui","orcid":"https://orcid.org/0000-0002-9889-2101"},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ge","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering, China"],"raw_orcid":"https://orcid.org/0000-0002-9889-2101","affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering, China","institution_ids":["https://openalex.org/I2802615301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110097903","display_name":"Xiao Jin","orcid":"https://orcid.org/0009-0007-3967-3033"},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Jin","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering, China"],"raw_orcid":"https://orcid.org/0009-0007-3967-3033","affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering, China","institution_ids":["https://openalex.org/I2802615301"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2802615301"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9932000041007996,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9932000041007996,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.991100013256073,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.810470700263977},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6626710891723633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6077100038528442},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5301355123519897},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4965689778327942},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.48202192783355713},{"id":"https://openalex.org/keywords/penetration","display_name":"Penetration (warfare)","score":0.44278684258461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43688011169433594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42654621601104736},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1586795151233673},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.10031783580780029},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.08279752731323242},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0672343373298645},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06007543206214905}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.810470700263977},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6626710891723633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6077100038528442},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5301355123519897},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4965689778327942},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.48202192783355713},{"id":"https://openalex.org/C80107235","wikidata":"https://www.wikidata.org/wiki/Q7162625","display_name":"Penetration (warfare)","level":2,"score":0.44278684258461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43688011169433594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42654621601104736},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1586795151233673},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.10031783580780029},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.08279752731323242},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0672343373298645},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06007543206214905},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650215.3650293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650215.3650293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Conference on Machine Learning and Computer Application","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3123348991","https://openalex.org/W3127561923","https://openalex.org/W4310705874","https://openalex.org/W6602223359","https://openalex.org/W6602599378","https://openalex.org/W6604425148"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2002320543","https://openalex.org/W2061947244","https://openalex.org/W2150232912","https://openalex.org/W1977959518","https://openalex.org/W2054940838"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"new":[4],"deep":[5,159,179],"reinforcement":[6,160,180],"learning":[7,130,161,181],"algorithm":[8,22,47,96,99],"DEU-DRQNper":[9,140],"is":[10,23],"proposed":[11],"for":[12,157],"penetration":[13,145,163,186],"test":[14,146,164],"path":[15,165],"planning":[16,166],"under":[17],"partially":[18],"observable":[19],"conditions.":[20],"The":[21,89,109],"improved":[24],"on":[25],"the":[26,32,38,52,58,74,79,115,121,176,183],"basis":[27],"of":[28,35,54,81,93,111,123,125,178,185],"DRQN":[29],"algorithm,":[30,50],"including":[31],"experience":[33,64,70,82],"playback":[34,65],"priority":[36,80],"sequence,":[37],"action":[39],"exploration":[40,91,103],"and":[41,48,51,97,104,128,170],"selection":[42],"strategy":[43,92],"combining":[44],"\u025b":[45,94],"greedy":[46,95],"UCB":[49,98],"way":[53],"Double":[55,112],"DQN":[56,113],"calculating":[57,114],"target":[59,116],"Q":[60],"value.":[61],"Priority":[62],"sequence":[63,171],"mechanism":[66],"selects":[67],"more":[68,131],"valuable":[69],"sequences":[71,83],"according":[72],"to":[73,78,86,102,162],"probability":[75],"distribution":[76],"corresponding":[77],"during":[84],"sampling":[85],"accelerate":[87],"learning.":[88],"hybrid":[90],"gives":[100],"consideration":[101],"utilization,":[105],"thus":[106],"improving":[107],"efficiency.":[108],"method":[110],"q":[117,126],"value":[118,127],"effectively":[119],"solves":[120],"problem":[122],"overestimation":[124],"makes":[129],"stable.":[132],"Experiments":[133],"in":[134,144,182],"several":[135],"simulation":[136],"environments":[137],"show":[138],"that":[139],"achieves":[141],"better":[142],"performance":[143],"scenarios":[147],"with":[148,167],"incomplete":[149],"state":[150],"observation,":[151],"which":[152],"provides":[153],"an":[154],"effective":[155],"solution":[156],"applying":[158],"partial":[168],"observability":[169],"dependence.":[172],"This":[173],"study":[174],"expands":[175],"application":[177],"field":[184],"testing.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}