Related papers: Robust Deep Reinforcement Learning through Bootstr…

Solving job shop scheduling problems (JSSPs) with a fixed strategy, such as a priority dispatching rule, may yield satisfactory results for several problem instances but, nevertheless, insufficient results for others. From this…

Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement Learning (RL). To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabilizing forces exercised…

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error,…

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real…

In recent years, Deep Reinforcement Learning (DRL) has emerged as a promising method for robot collision avoidance. However, such DRL models often come with limitations, such as adapting effectively to structured environments containing…

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Many state-of-the-art adversarial training methods for deep learning leverage upper bounds of the adversarial loss to provide security guarantees against adversarial attacks. Yet, these methods rely on convex relaxations to propagate lower…

This paper focuses on the critical load restoration problem in distribution systems following major outages. To provide fast online response and optimal sequential decision-making support, a reinforcement learning (RL) based approach is…

Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the…

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics. It has been widely adopted in the research of robotics,…

Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning…

Deep Metric Learning (DML) has shown remarkable successes in many domains by taking advantage of powerful deep neural networks. Deep neural networks are prone to adversarial attacks and could be easily fooled by adversarial examples. The…

Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep…

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

Robustness to modeling errors and uncertainties remains a central challenge in reinforcement learning (RL). In this work, we address this challenge by leveraging diffusion models to train robust RL policies. Diffusion models have recently…

We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…

This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments. In particular, an adaptive curriculum reinforcement learning…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment. As a primary countermeasure, adversarial training improves…