相关论文: Rigorous Agent Evaluation: An Adversarial Approach…

We show that adversarial reinforcement learning (ARL) can be used to produce market marking agents that are robust to adversarial and adaptively-chosen market conditions. To apply ARL, we turn the well-studied single-agent model of…

Autonomous vehicles (AVs) face significant threats to their safe operation in complex traffic environments. Adversarial training has emerged as an effective method of enabling AVs to preemptively fortify their robustness against malicious…

Autonomous vehicles inevitably encounter a vast array of scenarios in real-world environments. Addressing long-tail scenarios, particularly those involving intensive interactions with numerous traffic participants, remains one of the most…

Unmanned vehicles able to conduct advanced operations without human intervention are being developed at a fast pace for many purposes. Not surprisingly, they are also expected to significantly change how military operations can be…

Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to…

The increasing use of autonomous and semi-autonomous agents in society has made it crucial to validate their safety. However, the complex scenarios in which they are used may make formal verification impossible. To address this challenge,…

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of…

Establishing trustworthy safety assurance for autonomous driving systems (ADSs) requires evidence that failures arise from avoidable system deficiencies rather than unavoidable traffic conflicts. Current adversarial simulation methods can…

End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to…

Adversarial attacks can compromise the robustness of real-world detection models. However, evaluating these models under real-world conditions poses challenges due to resource-intensive experiments. Virtual simulations offer an alternative,…

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Safety evaluation of self-driving technologies has been extensively studied. One recent approach uses Monte Carlo based evaluation to estimate the occurrence probabilities of safety-critical events as safety measures. These Monte Carlo…

Evaluating failure probability for complex engineering systems is a computationally intensive task. While the Monte Carlo method is easy to implement, it converges slowly and, hence, requires numerous repeated simulations of a complex…

Deploying reinforcement learning agents in the real world can be challenging due to the risks associated with learning through trial and error. We propose a task-agnostic method that leverages small sets of safe and unsafe demonstrations to…

Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics should be chosen so as to capture the downstream impact of…

The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…

Implementing an autonomous vehicle that is able to output feasible, smooth and efficient trajectories is a long-standing challenge. Several approaches have been considered, roughly falling under two categories: rule-based and learning-based…

In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversarial game, where an adversary searches over reward models, and…