{"id":"https://openalex.org/W2965234432","doi":"https://doi.org/10.1609/aaai.v33i01.33019939","title":"Reinforcement Learning under Threats","display_name":"Reinforcement Learning under Threats","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2965234432","doi":"https://doi.org/10.1609/aaai.v33i01.33019939","mag":"2965234432"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019939","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019939","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5106/4979","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5106/4979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027805517","display_name":"V\u00edctor Gallego","orcid":"https://orcid.org/0000-0003-0349-0714"},"institutions":[{"id":"https://openalex.org/I4210157032","display_name":"Institute of Mathematical Sciences","ror":"https://ror.org/05e9bn444","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210157032"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Victor Gallego","raw_affiliation_strings":["Instituto de Ciencias Matem\u00e1ticas"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciencias Matem\u00e1ticas","institution_ids":["https://openalex.org/I4210157032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091548743","display_name":"Roi Naveiro","orcid":"https://orcid.org/0000-0001-9032-2465"},"institutions":[{"id":"https://openalex.org/I4210157032","display_name":"Institute of Mathematical Sciences","ror":"https://ror.org/05e9bn444","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210157032"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roi Naveiro","raw_affiliation_strings":["Instituto de Ciencias Matem\u00e1ticas"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciencias Matem\u00e1ticas","institution_ids":["https://openalex.org/I4210157032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065634152","display_name":"David R\u0131\u0301os Insua","orcid":"https://orcid.org/0000-0002-5748-9658"},"institutions":[{"id":"https://openalex.org/I4210157032","display_name":"Institute of Mathematical Sciences","ror":"https://ror.org/05e9bn444","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210157032"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Rios Insua","raw_affiliation_strings":["Instituto de Ciencias Matem\u00e1ticas"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciencias Matem\u00e1ticas","institution_ids":["https://openalex.org/I4210157032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027805517"],"corresponding_institution_ids":["https://openalex.org/I4210157032"],"apc_list":null,"apc_paid":null,"fwci":4.6752,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95309735,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"9939","last_page":"9940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9930999875068665,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9930999875068665,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9908999800682068,"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":0.9155041575431824},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7604979276657104},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.758778989315033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137358784675598},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.5496264696121216},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5031194090843201},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5024290084838867},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44346579909324646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43218088150024414},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.4193054139614105},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.386104553937912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3266400992870331},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2876005470752716},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.20687809586524963},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.19659623503684998},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08924201130867004},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06483960151672363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0642659068107605},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05974331498146057}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9155041575431824},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7604979276657104},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.758778989315033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137358784675598},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.5496264696121216},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5031194090843201},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5024290084838867},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44346579909324646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43218088150024414},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.4193054139614105},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.386104553937912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3266400992870331},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2876005470752716},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.20687809586524963},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.19659623503684998},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08924201130867004},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06483960151672363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0642659068107605},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05974331498146057},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019939","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019939","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5106/4979","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1809.01560","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.01560","pdf_url":"https://arxiv.org/pdf/1809.01560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:digital.csic.es:10261/347764","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.01560v2","pdf_url":"https://arxiv.org/pdf/1809.01560","source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019939","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019939","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5106/4979","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312059","display_name":"Instituto de Ciencias Matem\u00e1ticas","ror":"https://ror.org/05e9bn444"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965234432.pdf","grobid_xml":"https://content.openalex.org/works/W2965234432.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W201521870","https://openalex.org/W206679605","https://openalex.org/W1518931405","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1976450472","https://openalex.org/W2011353069","https://openalex.org/W2028145673","https://openalex.org/W2046289784","https://openalex.org/W2062663664","https://openalex.org/W2086997850","https://openalex.org/W2116067849","https://openalex.org/W2120846115","https://openalex.org/W2140443131","https://openalex.org/W2145339207","https://openalex.org/W2561776174","https://openalex.org/W2766447205","https://openalex.org/W2768908787","https://openalex.org/W2773446523","https://openalex.org/W2941205169","https://openalex.org/W2949103145","https://openalex.org/W2949475445","https://openalex.org/W2952603690","https://openalex.org/W2963035419","https://openalex.org/W4214717370","https://openalex.org/W4243845907","https://openalex.org/W4247200422","https://openalex.org/W4248012565","https://openalex.org/W4292230443","https://openalex.org/W4300427736","https://openalex.org/W6608549526"],"related_works":["https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W2914760492","https://openalex.org/W4378501524","https://openalex.org/W1964650011","https://openalex.org/W2295963756","https://openalex.org/W2047932101","https://openalex.org/W2893113448","https://openalex.org/W2586549768"],"abstract_inverted_index":{"In":[0],"several":[1],"reinforcement":[2],"learning":[3,109],"(RL)":[4],"scenarios,":[5],"mainly":[6],"in":[7,106],"security":[8],"settings,":[9],"there":[10],"may":[11],"be":[12],"adversaries":[13],"trying":[14],"to":[15,32,44,67,87,111],"interfere":[16],"with":[17,113],"the":[18,51,62,85,121],"reward":[19],"generating":[20],"process.":[21],"However,":[22],"when":[23],"non-stationary":[24],"environments":[25],"as":[26,55],"such":[27],"are":[28],"considered,":[29],"Q-learning":[30],"leads":[31],"suboptimal":[33],"results":[34],"(Busoniu,":[35],"Babuska,":[36],"and":[37],"De":[38],"Schutter":[39],"2010).":[40],"Previous":[41],"game-theoretical":[42],"approaches":[43],"this":[45,90],"problem":[46,63],"have":[47],"focused":[48],"on":[49],"modeling":[50],"whole":[52],"multi-agent":[53],"system":[54],"a":[56,68,77,101,107],"game.":[57],"Instead,":[58],"we":[59,99],"shall":[60],"face":[61],"of":[64,123],"prescribing":[65],"decisions":[66],"single":[69],"agent":[70],"(the":[71,81],"supported":[72],"decision":[73],"maker,":[74],"DM)":[75],"against":[76],"potential":[78],"threat":[79],"model":[80],"adversary).":[82],"We":[83,115],"augment":[84],"MDP":[86],"account":[88],"for":[89],"threat,":[91],"introducing":[92],"Threatened":[93],"Markov":[94],"Decision":[95],"Processes":[96],"(TMDPs).":[97],"Furthermore,":[98],"propose":[100],"level-k":[102],"thinking":[103],"scheme":[104],"resulting":[105],"new":[108],"framework":[110],"deal":[112],"TMDPs.":[114],"empirically":[116],"test":[117],"our":[118],"framework,":[119],"showing":[120],"benefits":[122],"opponent":[124],"modeling.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
