{"id":8687,"date":"2023-07-21T11:22:59","date_gmt":"2023-07-21T11:22:59","guid":{"rendered":"https:\/\/komorebi.ai\/?page_id=8687"},"modified":"2023-09-21T10:27:15","modified_gmt":"2023-09-21T10:27:15","slug":"reinforcement-learning-under-threats","status":"publish","type":"page","link":"https:\/\/komorebi.ai\/es\/reinforcement-learning-under-threats\/","title":{"rendered":"Reinforcement Learning under Threats"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Reinforcement Learning under Threats\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Proceedings of the AAAI Conference on Artificial Intelligence, 2022<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Abstract<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The study introduces the concept of <\/span>Threatened Markov Decision Processes (TMDPs)<\/b> to address the issue of suboptimal results from Q-learning in reinforcement learning scenarios where adversaries may interfere with the reward generation process.\u00a0<\/span><\/p>

Rather than viewing the multi-agent system as a game, the focus is on decision-making for a single agent against a potential adversary. Through this model and <\/span>a proposed level-k thinking scheme<\/b>, a new learning framework is developed to handle TMDPs, with empirical tests demonstrating the benefits of this opponent modeling approach.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

The study introduces Threatened Markov Decision Processes and a level-k reasoning approach for enhanced decision-making in adversarial reinforcement learning scenarios, relevant to cybersecurity, finance, and AI.\n<\/p><\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Where does it apply?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The Threatened Markov Decision Processes (TMDPs) and level-k reasoning approach are applicable in industries where <\/span>decision-making<\/b> occurs in potentially adversarial or competitive environments.\u00a0<\/span><\/p>

These include, but are not limited to, <\/span>cybersecurity <\/b>(for detecting and mitigating threats), <\/span>finance <\/b>(for trading strategies in competitive markets), <\/span>strategic business decisions<\/b> in competitive industries, and areas of artificial intelligence and machine learning where robust adversarial training is necessary.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Adversarial\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Why does it matters?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Threatened Markov Decision Processes (TMDPs) matter because they provide a<\/span> framework<\/b> to assist decision-makers <\/span>in reinforcement learning scenarios <\/b>where adversarial interference impacts the reward generation process.\u00a0<\/span><\/p>

The level-k reasoning method for modeling adversarial behavior also offers a novel approach to enhance decision-making under threat models.\u00a0<\/span><\/p>

Such an approach is crucial in enhancing the robustness and flexibility of AI systems in various fields, including cybersecurity, where the presence of adversarial instances is a significant concern.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Reinforcement Learning under Threats\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Proceedings of the AAAI Conference on Artificial Intelligence, 2022<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\"\"<\/a>\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\tVictor Gallego <\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tChief Research Officer<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tReinforcement Learning, Decision Making<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t<\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\tSource<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Reinforcement\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Otras publicaciones<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Current\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"industria\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Joint\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Avances Actuales en Redes Neuronales\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Producci\u00f3n de hadrones mediante dijets inclusivos con veto en rapidez\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Asociaci\u00f3n conjunta de la actividad f\u00edsica e \u00edndice de masa corporal con el riesgo cardiovascular<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

El art\u00edculo revisa el progreso de las redes neuronales enfatizando enfoques bayesianos y destaca su relevancia en an\u00e1lisis predictivos, an\u00e1lisis del comportamiento del cliente y gesti\u00f3n de riesgos en sectores empresariales.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

El estudio explora par\u00e1metros para la expansi\u00f3n perturbativa en la colisi\u00f3n de part\u00edculas, ayudando al entendimiento de la f\u00edsica de part\u00edculas. En el largo plazo, aplica a campos como la computaci\u00f3n cu\u00e1ntica, la tecnolog\u00eda de la salud y la energ\u00eda nuclear.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

El estudio refuta la paradoja de estar \u00abcon sobrepeso pero en forma\u00bb, destacando la importancia de la p\u00e9rdida de peso en combinaci\u00f3n con la actividad f\u00edsica para aliviar los riesgos de enfermedades cardiovasculares.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tNeural networks, customer behavior analysis<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tParticle Physics, Big Data<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tData Analytics, Public health<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Saber m\u00e1s >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Saber m\u00e1s >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Saber m\u00e1s >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Reinforcement Learning under Threats Proceedings of the AAAI Conference on Artificial Intelligence, 2022 Abstract The study introduces the concept of Threatened Markov Decision Processes (TMDPs) to address the issue of suboptimal results from Q-learning in reinforcement learning scenarios where adversaries may interfere with the reward generation process. Rather than viewing the multi-agent system as a […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"yoast_head":"\nReinforcement Learning under Threats - Komorebi AI<\/title>\n<meta name=\"description\" content=\"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/komorebi.ai\/es\/reinforcement-learning-under-threats\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Reinforcement Learning under Threats - Komorebi AI\" \/>\n<meta property=\"og:description\" content=\"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/komorebi.ai\/es\/reinforcement-learning-under-threats\/\" \/>\n<meta property=\"og:site_name\" content=\"Komorebi AI\" \/>\n<meta property=\"article:modified_time\" content=\"2023-09-21T10:27:15+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/komorebi.ai\/wp-content\/uploads\/2023\/07\/ciberseguridad-2.jpg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/\",\"url\":\"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/\",\"name\":\"Reinforcement Learning under Threats - Komorebi AI\",\"isPartOf\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#website\"},\"datePublished\":\"2023-07-21T11:22:59+00:00\",\"dateModified\":\"2023-09-21T10:27:15+00:00\",\"description\":\"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.\",\"breadcrumb\":{\"@id\":\"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Portada\",\"item\":\"https:\/\/komorebi.ai\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Reinforcement Learning under Threats\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/komorebi.ai\/es\/#website\",\"url\":\"https:\/\/komorebi.ai\/es\/\",\"name\":\"Komorebi AI\",\"description\":\"Komorebi\",\"publisher\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/komorebi.ai\/es\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/komorebi.ai\/es\/#organization\",\"name\":\"Komorebi AI\",\"url\":\"https:\/\/komorebi.ai\/es\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png\",\"contentUrl\":\"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png\",\"width\":456,\"height\":277,\"caption\":\"Komorebi AI\"},\"image\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Reinforcement Learning under Threats - Komorebi AI","description":"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/komorebi.ai\/es\/reinforcement-learning-under-threats\/","og_locale":"es_ES","og_type":"article","og_title":"Reinforcement Learning under Threats - Komorebi AI","og_description":"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.","og_url":"https:\/\/komorebi.ai\/es\/reinforcement-learning-under-threats\/","og_site_name":"Komorebi AI","article_modified_time":"2023-09-21T10:27:15+00:00","og_image":[{"url":"https:\/\/komorebi.ai\/wp-content\/uploads\/2023\/07\/ciberseguridad-2.jpg"}],"twitter_card":"summary_large_image","twitter_misc":{"Tiempo de lectura":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/","url":"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/","name":"Reinforcement Learning under Threats - Komorebi AI","isPartOf":{"@id":"https:\/\/komorebi.ai\/es\/#website"},"datePublished":"2023-07-21T11:22:59+00:00","dateModified":"2023-09-21T10:27:15+00:00","description":"Threatened Markov processes and level-k reasoning for decision-making in adversarial reinforcement learning, aiding cybersecurity and AI.","breadcrumb":{"@id":"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/komorebi.ai\/reinforcement-learning-under-threats\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/komorebi.ai\/"},{"@type":"ListItem","position":2,"name":"Reinforcement Learning under Threats"}]},{"@type":"WebSite","@id":"https:\/\/komorebi.ai\/es\/#website","url":"https:\/\/komorebi.ai\/es\/","name":"Komorebi AI","description":"Komorebi","publisher":{"@id":"https:\/\/komorebi.ai\/es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/komorebi.ai\/es\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"es"},{"@type":"Organization","@id":"https:\/\/komorebi.ai\/es\/#organization","name":"Komorebi AI","url":"https:\/\/komorebi.ai\/es\/","logo":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/","url":"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png","contentUrl":"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png","width":456,"height":277,"caption":"Komorebi AI"},"image":{"@id":"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/pages\/8687"}],"collection":[{"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/comments?post=8687"}],"version-history":[{"count":23,"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/pages\/8687\/revisions"}],"predecessor-version":[{"id":9827,"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/pages\/8687\/revisions\/9827"}],"wp:attachment":[{"href":"https:\/\/komorebi.ai\/es\/wp-json\/wp\/v2\/media?parent=8687"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}