相关论文: Measuring and Mitigating Interference in Reinforce…

The great performance of machine learning algorithms and deep neural networks in several perception and control tasks is pushing the industry to adopt such technologies in safety-critical applications, as autonomous robots and self-driving…

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

With the development of experimental quantum technology, quantum control has attracted increasing attention due to the realization of controllable artificial quantum systems. However, because quantum-mechanical systems are often too…

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous cars. Key performance factors are a fine range resolution and the possibility to directly measure velocity. With a rising number of…

This work describes a technique for active rejection of multiple independent and time-correlated stochastic disturbances for a nonlinear flexible inverted pendulum with cart system with uncertain model parameters. The control law is…

We propose a new method to probe the learning mechanism of Deep Neural Networks (DNN) by perturbing the system using Noise Injection Nodes (NINs). These nodes inject uncorrelated noise via additional optimizable weights to existing…

In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. To mitigate the limitations of robustness, we introduce a new measure called…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the…

Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such methods often…

The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, target networks notoriously require additional memory and delay…

Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are…

Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs. Modern methods for bearing fault diagnosis rely heavily on vibration analysis and machine learning techniques, which often require…

Deep neural networks (DNNs) have achieved superior performance in various prediction tasks, but can be very vulnerable to adversarial examples or perturbations. Therefore, it is crucial to measure the sensitivity of DNNs to various forms of…

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems…

Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and must be accounted for…

Power systems must maintain the frequency within acceptable limits when subjected to a disturbance. To ensure this, the most significant credible disturbance in the system is normally used as a benchmark to allocate the Primary Frequency…

In the current era of quantum computing, robust and efficient tools are essential to bridge the gap between simulations and quantum hardware execution. In this work, we introduce a machine learning approach to characterize the noise…

Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits learning. We test this hypothesis through a large-scale…

Deep reinforcement learning has been successfully used in many dynamic decision making domains, especially those with very large state spaces. However, it is also well-known that deep reinforcement learning can be very slow and resource…