Related papers: Consolidated Adaptive T-soft Update for Deep Reinf…
Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overfitting, i.e., the robustness will drop sharply at a certain…
Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of…
Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against $\ell_2$ norm bounded…
Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving. However, despite their advanced capabilities, DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in…
Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goal of maximizing the…
This paper introduces a Deep Reinforcement Learning (DRL) based TCP congestion-control algorithm that uses a Deep Q-Network (DQN) to adapt the congestion window (cWnd) dynamically based on observed network state. The proposed approach…
In decentralized federated learning (DFL), the presence of abnormal clients, often caused by noisy or poisoned data, can significantly disrupt the learning process and degrade the overall robustness of the model. Previous methods on this…
In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve. Standard decay schedulers assume monotonic…
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…
Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is…
Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in…
The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices around the world, where the IoT devices collect and share information to reflect status of the physical world. The Autonomous Control System (ACS),…
Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems since they do not require access to target models. Adversarial training (AT), which is recognized as the strongest defense against white-box…
The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…
Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and…
Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation…
We solve active target tracking, one of the essential tasks in autonomous systems, using a deep reinforcement learning (RL) approach. In this problem, an autonomous agent is tasked with acquiring information about targets of interests using…
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…
Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge…
Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller…