Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent
agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of …

Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for
tasks where complex policies are learned within reactive systems. Unfortunately, these …

Formally verifying deep reinforcement learning (DRL) systems suffers from both inaccurate
verification results and limited scalability. The major obstacle lies in the large overestimation …

In this short paper, we present our ongoing work on the veriFIRE project—a collaboration
between industry and academia, aimed at using verification for increasing the reliability of a …

This paper presents COOL-MC, a tool that integrates state-of-the-art reinforcement learning
(RL) and model checking. Specifically, the tool builds upon the OpenAI gym and the …

This paper proposes a novel, abstraction-based, certified training method for robust image
classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding …

We present a verification-based learning framework VEL that synthesizes safe programmatic
controllers for environments with continuous state and action spaces. The key idea is the …

In embedded systems, applications frequently have to meet non-functional requirements
regarding, eg, real-time or energy consumption constraints, when executing on a given …

Deep Reinforcement Learning (DRL) is critical in modern Artificial Intelligence (AI), powering
innovations from gaming to autonomous vehicles. As DRL continues its rapid ascent …

The rapid advance of deep reinforcement learning techniques enables the oversight of
safety-critical systems through the utilization of Deep Neural Networks (DNNs). This …