arXiv:2511.07564v1 Announce Type: cross 
Abstract: Active flow control of compressible transonic shock-boundary layer interactions over a two-dimensional RAE2822 airfoil at Re = 50,000 is investigated using deep reinforcement learning (DRL). The flow field exhibits highly unsteady dynamics, including complex shock-boundary layer interactions, shock oscillations, and the generation of Kutta waves from the trailing edge. A high-fidelity CFD solver, employing a fifth-order spectral discontinuous Galerkin scheme in space and a strong-stability-preserving Runge-Kutta (5,4) method in time, together with adaptive mesh refinement capability, is used to obtain the accurate flow field. Synthetic jet actuation is employed to manipulate these unsteady flow features, while the DRL agent autonomously discovers effective control strategies through direct interaction with high-fidelity compressible flow simulations. The trained controllers effectively mitigate shock-induced separation, suppress unsteady oscillations, and manipulate aerodynamic forces under transonic conditions. In the first set of experiments, aimed at both drag reduction and lift enhancement, the DRL-based control reduces the average drag coefficient by 13.78% and increases lift by 131.18%, thereby improving the lift-to-drag ratio by 121.52%, which underscores its potential for managing complex flow dynamics. In the second set, targeting drag reduction while maintaining lift, the DRL-based control achieves a 25.62% reduction in drag and a substantial 196.30% increase in lift, accompanied by markedly diminished oscillations. In this case, the lift-to-drag ratio improves by 220.26%.

تستكشف دراسة نُشرت في 12 نوفمبر 2025 استخدام التعلم العميق المعزز (DRL) للتحكم في تدفق الهواء الضاغط فوق جناح RAE2822 عند عدد رينولدز يبلغ 50,000. تتناول البحث التفاعلات المعقدة بين الصدمات وطبقة الحدود، وتهدف إلى تحسين الأداء الديناميكي الهوائي. من خلال استخدام تنشيط النفاثات الاصطناعية وحل معادلات ديناميكا السوائل الحسابية (CFD) عالية الدقة، يطور وكيل DRL استراتيجيات تحكم فعالة بشكل مستقل. تُظهر النتائج انخفاضًا كبيرًا في السحب بنسبة 13.78% وزيادة في الرفع بنسبة 131.18%، مما يؤدي إلى تحسين بنسبة 121.52% في نسبة الرفع إلى السحب. يُعد هذا التقدم في إدارة الديناميات المعقدة للتدفق أمرًا حيويًا لتحسين كفاءة الأنظمة الديناميكية الهوائية.

Un estudio publicado el 12 de noviembre de 2025 investiga el uso del aprendizaje por refuerzo profundo (DRL) para controlar el flujo compresible transónico sobre un perfil aerodinámico RAE2822 a un número de Reynolds de 50,000. La investigación aborda interacciones complejas entre choques y capas límite, y busca mejorar el rendimiento aerodinámico. Al emplear activación de chorro sintético y un solucionador de dinámica de fluidos computacional (CFD) de alta fidelidad, el agente DRL desarrolla de manera autónoma estrategias de control efectivas. Los resultados muestran una reducción significativa de la resistencia del 13.78% y un aumento de la sustentación del 131.18%, lo que lleva a una mejora del 121.52% en la relación sustentación-resistencia. Este avance en la gestión de dinámicas de flujo complejas es crucial para mejorar la eficiencia de los sistemas aerodinámicos.

Une étude publiée le 12 novembre 2025 explore l'utilisation de l'apprentissage par renforcement profond (DRL) pour contrôler l'écoulement compressible transonique sur un profil aérodynamique RAE2822 à un nombre de Reynolds de 50 000. La recherche aborde des interactions complexes entre les chocs et la couche limite et vise à améliorer les performances aérodynamiques. En utilisant une action de jet synthétique et un solveur de dynamique des fluides computationnelle (CFD) de haute fidélité, l'agent DRL développe de manière autonome des stratégies de contrôle efficaces. Les résultats montrent une réduction significative de la traînée de 13,78 % et une augmentation de la portance de 131,18 %, entraînant une amélioration de 121,52 % du rapport portance/traînée. Cette avancée dans la gestion des dynamiques d'écoulement complexes est cruciale pour améliorer l'efficacité des systèmes aérodynamiques.

A study published on November 12, 2025, explores the use of deep reinforcement learning (DRL) to control transonic compressible flow over an RAE2822 airfoil at a Reynolds number of 50,000. The research addresses complex shock-boundary layer interactions and aims to improve aerodynamic performance. By employing synthetic jet actuation and a high-fidelity computational fluid dynamics (CFD) solver, the DRL agent autonomously develops effective control strategies. The results show a significant reduction in drag by 13.78% and an increase in lift by 131.18%, leading to a 121.52% improvement in the lift-to-drag ratio. This advancement in managing complex flow dynamics is crucial for enhancing the efficiency of aerodynamic systems.

Shocks Under Control: Taming Transonic Compressible Flow over an RAE2822 Airfoil with Deep Reinforcement Learning

Although Black Friday is still two weeks away, you can find great Nintendo Switch and Switch 2 deals now. I've collected the best from Walmart, Best Buy, and more.

مع اقتراب يوم الجمعة السوداء بعد أسبوعين، تتوفر بالفعل عروض مبكرة على أجهزة نينتندو سويتش وسويتش 2. تقدم متاجر كبيرة مثل وول مارت وبيست باي أكثر من 20 عرضًا، مما يوفر للمستهلكين فرصة لتوفير المال على منتجات الألعاب الشهيرة قبل موسم التسوق للعطلات.

A medida que se acerca el Black Friday en dos semanas, ya están disponibles ofertas anticipadas en las consolas Nintendo Switch y Switch 2. Grandes minoristas como Walmart y Best Buy están ofreciendo más de 20 ventas, brindando a los consumidores la oportunidad de ahorrar en productos de videojuegos populares antes de la locura de compras navideñas.

À l'approche de Black Friday dans deux semaines, des offres anticipées sur les consoles Nintendo Switch et Switch 2 sont déjà disponibles. Des détaillants majeurs comme Walmart et Best Buy proposent plus de 20 ventes, offrant aux consommateurs l'occasion d'économiser sur des produits de jeu populaires avant la ruée des achats de vacances.

As Black Friday approaches in two weeks, early deals on Nintendo Switch and Switch 2 consoles are already available. Major retailers like Walmart and Best Buy are offering over 20 sales, providing consumers with an opportunity to save on popular gaming products ahead of the holiday shopping rush.

Best early Black Friday Nintendo Switch deals 2025: 20+ sales out early

ZDNET sat down with Andrew Ng at AI Dev 25 in New York to talk about developer futures, responsible AI, and why AGI is overhyped.

You should still learn to code, says top Google AI exec - here's why

Black Friday is just over one week away, but you can get a jump on your holiday shopping list with great deals on gaming desktop PCs, monitors, SSDs, and more.

Best early Black Friday gaming PC deals 2025: My favorite sales out early

Although Black Friday is still two weeks away, you can find great PlayStation deals now from across the internet. I've collected some of the best.

على الرغم من أن يوم الجمعة السوداء لا يزال بعيدًا لمدة أسبوعين، إلا أن هناك بالفعل عروض رائعة على بلاي ستيشن متاحة عبر الإنترنت. يبرز المقال أكثر من 20 عرضًا يمكن العثور عليها عبر منصات مختلفة، مما يوفر فرصة مبكرة للمتسوقين للاستفادة من الخصومات قبل التاريخ الرسمي ليوم الجمعة السوداء.

Aunque el Black Friday aún está a dos semanas de distancia, ya hay excelentes ofertas de PlayStation disponibles en línea. El artículo destaca más de 20 ventas que se pueden encontrar en varias plataformas, brindando una oportunidad anticipada para que los compradores aprovechen los descuentos antes de la fecha oficial del Black Friday.

Bien que le Black Friday soit encore dans deux semaines, il existe déjà d'excellentes offres PlayStation disponibles en ligne. L'article met en avant plus de 20 ventes que l'on peut trouver sur diverses plateformes, offrant ainsi une occasion précoce aux acheteurs de profiter des réductions avant la date officielle du Black Friday.

Although Black Friday is still two weeks away, there are already great PlayStation deals available online. The article highlights over 20 sales that can be found across various platforms, providing an early opportunity for shoppers to take advantage of discounts ahead of the official Black Friday date.

Best early Black Friday PlayStation deals 2025: 20+ sales out now

Black Friday is just over a week away, and you can already find great deals on TVs and home theater equipment from Samsung, Sony, and more.

Best early Black Friday TV deals 2025: Save on Samsung, TCL, and more

This new AI coding environment looks like a real winner. Here's why.

Google's Antigravity puts coding productivity before AI hype - and the result is astonishing

arXiv:2406.11281v2 Announce Type: replace 
Abstract: We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply chains, finance, manufacturing, services, and dynamic games--the state-transition mechanism is determined by system design, while available data capture the distributional properties of the stochastic inputs from the environment. For modeling and computational tractability, a decision maker often adopts a Markov control model with i.i.d. environment inputs, which can render learned policies fragile to internal dependence or external perturbations. We introduce a distributionally robust stochastic control paradigm that promotes policy reliability by introducing adaptive adversarial perturbations to the environment input, while preserving the modeling, statistical, and computational tractability of the Markovian formulation. From a modeling perspective, we examine two adversary models--current-action-aware and current-action-unaware--leading to distinct dynamic behaviors and robust optimal policies. From a statistical learning perspective, we characterize optimal finite-sample minimax rates for uniform learning of the robust value function across a continuum of states under ambiguity sets defined by the $f_k$-divergence and Wasserstein distance. To efficiently compute the optimal robust policies, we further propose algorithms inspired by deep reinforcement learning methodologies. Finally, we demonstrate the applicability of the framework to real managerial problems.

تتناول الدراسة التعلم القائم على البيانات للتحكم الاستوكاستيكي القوي للأنظمة ذات الأفق اللانهائي مع مساحات حالة وإجراء مستمرة. تسلط الضوء على هشاشة السياسات المتعلمة عند استخدام نماذج التحكم ماركوف التقليدية مع مدخلات مستقلة وموزعة بشكل متطابق. يقترح المؤلفون نموذجًا للتحكم الاستوكاستيكي القوي من منظور التوزيع يعزز موثوقية السياسات من خلال إدخال اضطرابات عدائية تكيفية، مع الحفاظ على مزايا الإطار الماركوفي.

El estudio se centra en el aprendizaje basado en datos del control estocástico robusto para sistemas de horizonte infinito con espacios de estado y acción continuos. Destaca la fragilidad de las políticas aprendidas al utilizar modelos de control de Markov tradicionales con entradas independientes e idénticamente distribuidas. Los autores proponen un paradigma de control estocástico robusto desde el punto de vista de la distribución que mejora la fiabilidad de las políticas mediante perturbaciones adversariales adaptativas, manteniendo las ventajas del marco markoviano.

L'étude se concentre sur l'apprentissage basé sur les données du contrôle stochastique robuste pour des systèmes à horizon infini avec des espaces d'état et d'action continus. Elle met en évidence la fragilité des politiques apprises lors de l'utilisation de modèles de contrôle de Markov traditionnels avec des entrées indépendantes et identiquement distribuées. Les auteurs proposent un paradigme de contrôle stochastique robuste distributionnel qui améliore la fiabilité des politiques grâce à des perturbations adversariales adaptatives, tout en maintenant les avantages du cadre markovien.

The study focuses on data-driven learning of robust stochastic control for infinite-horizon systems with continuous state and action spaces. It highlights the fragility of learned policies when using traditional Markov control models with independent and identically distributed inputs. The authors propose a distributionally robust stochastic control paradigm that enhances policy reliability through adaptive adversarial perturbations, while maintaining the advantages of the Markovian framework.

Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces

arXiv:2508.18839v2 Announce Type: replace 
Abstract: Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanisms, struggle to maintain performance under concept drift in malware domains, as their supervised learning formulation cannot optimize when to defer decisions to manual labeling and adaptation. Modern malware detection pipelines combine classifiers with monthly active learning (AL) and rejection mechanisms to mitigate the impact of concept drift. In this work, we develop a novel formulation of malware detection as a one-step Markov Decision Process and train a deep reinforcement learning (DRL) agent, simultaneously optimizing sample classification performance and rejecting high-risk samples for manual labeling. We evaluated the joint detection and drift mitigation policy learned by the DRL-based Malware Detection (DRMD) agent through time-aware evaluations on Android malware datasets subject to realistic drift requiring multi-year performance stability. The policies learned under these conditions achieve a higher Area Under Time (AUT) performance compared to standard classification approaches used in the domain, showing improved resilience to concept drift. Specifically, the DRMD agent achieved an average AUT improvement of 8.66 and 10.90 for the classification-only and classification-rejection policies, respectively. Our results demonstrate for the first time that DRL can facilitate effective malware detection and improved resiliency to concept drift in the dynamic setting of Android malware detection.

تتناول ورقة البحث بعنوان 'DRMD: التعلم العميق المعزز لاكتشاف البرمجيات الضارة تحت انحراف المفاهيم' التحديات المتعلقة باكتشاف البرمجيات الضارة في البيئات الديناميكية. تبرز الورقة قيود المصنفات التقليدية في التكيف مع التهديدات المتطورة وتقترح نهجًا مبتكرًا باستخدام التعلم العميق المعزز (DRL). يقوم وكيل DRL بتحسين أداء تصنيف العينات بينما يدير العينات عالية المخاطر للتصنيف اليدوي، مما يظهر تحسينات في مقاييس الأداء مقارنة بالطرق القياسية.

El artículo de investigación titulado 'DRMD: Aprendizaje por refuerzo profundo para la detección de malware bajo deriva conceptual' aborda los desafíos de la detección de malware en entornos dinámicos. Destaca las limitaciones de los clasificadores tradicionales para adaptarse a amenazas en evolución y propone un enfoque novedoso utilizando aprendizaje por refuerzo profundo (DRL). El agente DRL optimiza el rendimiento de clasificación de muestras mientras gestiona muestras de alto riesgo para etiquetado manual, demostrando métricas de rendimiento mejoradas en comparación con métodos estándar.

L'article de recherche intitulé 'DRMD : Apprentissage par renforcement profond pour la détection de logiciels malveillants sous dérive conceptuelle' aborde les défis de la détection de logiciels malveillants dans des environnements dynamiques. Il met en évidence les limites des classificateurs traditionnels à s'adapter aux menaces évolutives et propose une approche novatrice utilisant l'apprentissage par renforcement profond (DRL). L'agent DRL optimise la classification des échantillons tout en gérant les échantillons à haut risque pour un étiquetage manuel, démontrant des performances amélior…

The research paper titled 'DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift' addresses the challenges of malware detection in dynamic environments. It highlights the limitations of traditional classifiers in adapting to evolving threats and proposes a novel approach using deep reinforcement learning (DRL). The DRL agent optimizes sample classification while managing high-risk samples for manual labeling, demonstrating improved performance metrics over standard methods.

DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift

arXiv:2511.10809v2 Announce Type: replace 
Abstract: Linear Predictive Clustering (LPC) partitions samples based on shared linear relationships between feature and target variables, with numerous applications including marketing, medicine, and education. Greedy optimization methods, commonly used for LPC, alternate between clustering and linear regression but lack global optimality. While effective for separable clusters, they struggle in non-separable settings where clusters overlap in feature space. In an alternative constrained optimization paradigm, Bertsimas and Shioda (2007) formulated LPC as a Mixed-Integer Program (MIP), ensuring global optimality regardless of separability but suffering from poor scalability. This work builds on the constrained optimization paradigm to introduce two novel approaches that improve the efficiency of global optimization for LPC. By leveraging key theoretical properties of separability, we derive near-optimal approximations with provable error bounds, significantly reducing the MIP formulation's complexity and improving scalability. Additionally, we can further approximate LPC as a Quadratic Pseudo-Boolean Optimization (QPBO) problem, achieving substantial computational improvements in some settings. Comparative analyses on synthetic and real-world datasets demonstrate that our methods consistently achieve near-optimal solutions with substantially lower regression errors than greedy optimization while exhibiting superior scalability over existing MIP formulations.

Near-optimal Linear Predictive Clustering in Non-separable Spaces via Mixed Integer Programming and Quadratic Pseudo-Boolean Reductions

arXiv:2511.07947v2 Announce Type: replace-cross 
Abstract: Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking counters MEAs by embedding forensic markers for ownership verification. Current black-box watermarks prioritize MEA survival through representation entanglement, yet inadequately explore resilience against sequential MEAs and removal attacks. Our study reveals that this risk is underestimated because existing removal methods are weakened by entanglement. To address this gap, we propose Watermark Removal attacK (WRK), which circumvents entanglement constraints by exploiting decision boundaries shaped by prevailing sample-level watermark artifacts. WRK effectively reduces watermark success rates by at least 88.79% across existing watermarking benchmarks.
  For robust protection, we propose Class-Feature Watermarks (CFW), which improve resilience by leveraging class-level artifacts. CFW constructs a synthetic class using out-of-domain samples, eliminating vulnerable decision boundaries between original domain samples and their artifact-modified counterparts (watermark samples). CFW concurrently optimizes both MEA transferability and post-MEA stability. Experiments across multiple domains show that CFW consistently outperforms prior methods in resilience, maintaining a watermark success rate of at least 70.15% in extracted models even under the combined MEA and WRK distortion, while preserving the utility of protected models.

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

arXiv:2511.06854v2 Announce Type: replace-cross 
Abstract: Irregularly sampled time series (ISTS), characterized by non-uniform time intervals with natural missingness, are prevalent in real-world applications. Existing approaches for ISTS modeling primarily rely on observed values to impute unobserved ones or infer latent dynamics. However, these methods overlook a critical source of learning signal: the reconstruction error inherently produced during model training. Such error implicitly reflects how well a model captures the underlying data structure and can serve as an informative proxy for unobserved values. To exploit this insight, we propose iTimER, a simple yet effective self-supervised pre-training framework for ISTS representation learning. iTimER models the distribution of reconstruction errors over observed values and generates pseudo-observations for unobserved timestamps through a mixup strategy between sampled errors and the last available observations. This transforms unobserved timestamps into noise-aware training targets, enabling meaningful reconstruction signals. A Wasserstein metric aligns reconstruction error distributions between observed and pseudo-observed regions, while a contrastive learning objective enhances the discriminability of learned representations. Extensive experiments on classification, interpolation, and forecasting tasks demonstrate that iTimER consistently outperforms state-of-the-art methods under the ISTS setting.

تُعتبر السلاسل الزمنية المأخوذة بشكل غير منتظم (ISTS) شائعة في التطبيقات الواقعية، حيث تتميز بفترات زمنية غير متساوية وغيابات طبيعية. تعتمد الأساليب الحالية لنمذجة ISTS بشكل أساسي على القيم المرصودة لاستنتاج القيم غير المرصودة، متجاهلة إشارة التعلم الناتجة عن خطأ إعادة البناء الذي يتم إنتاجه أثناء تدريب النموذج. يقترح الإطار المقترح iTimER استغلال هذا الخطأ في إعادة البناء لتحسين تعلم التمثيل من خلال توليد ملاحظات زائفة للعلامات الزمنية غير المرصودة، مما يحسن نمذجة ISTS.

Las series temporales muestreadas de manera irregular (ISTS) son comunes en aplicaciones del mundo real, caracterizadas por intervalos de tiempo no uniformes y ausencias naturales. Los métodos existentes para la modelización de ISTS suelen depender de valores observados para inferir los no observados, ignorando la señal de aprendizaje proveniente del error de reconstrucción generado durante el entrenamiento del modelo. El marco propuesto iTimER aprovecha este error de reconstrucción para mejorar el aprendizaje de la representación generando pseudo-observaciones para marcas de tiempo no observa…

Les séries temporelles échantillonnées de manière irrégulière (ISTS) sont courantes dans les applications réelles, caractérisées par des intervalles de temps non uniformes et des absences naturelles. Les méthodes traditionnelles de modélisation des ISTS s'appuient souvent sur des valeurs observées pour inférer celles non observées, négligeant le signal d'apprentissage provenant de l'erreur de reconstruction produite lors de l'entraînement du modèle. Le cadre proposé iTimER exploite cette erreur de reconstruction pour améliorer l'apprentissage de la représentation en générant des pseudo-observa…

Irregularly sampled time series (ISTS) are common in real-world applications, characterized by non-uniform time intervals and natural missingness. Traditional ISTS modeling methods often rely on observed values to infer unobserved ones, neglecting the learning signal from reconstruction error produced during model training. The proposed iTimER framework leverages this reconstruction error to enhance representation learning by generating pseudo-observations for unobserved timestamps, thus improving the modeling of ISTS.

Shocks Under Control: Taming Transonic Compressible Flow over an RAE2822 Airfoil with Deep Reinforcement Learning

Was this article worth reading? Share it