Model-based reinforcement learning has been widely studied for controller synthesis in
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …

There has been significant recent interest in devising verification techniques for learning-
enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of …

Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating
agents that control autonomous systems. However, the" black box" nature of DRL agents …

In the current control design of safety-critical autonomous systems, formal verification
techniques are typically applied after the controller is designed to evaluate whether the …

Reinforcement Learning (RL) algorithms have found limited success beyond simulated
applications, and one main reason is the absence of safety guarantees during the learning …

Abstract Deep Reinforcement Learning (DRL) has demonstrated its strength in developing
intelligent systems. These systems shall be formally guaranteed to be trustworthy when …

Machine and reinforcement learning (RL) are increasingly being applied to plan and control
the behavior of autonomous systems interacting with the physical world. Examples include …

There is recent interest in using deep neural networks (DNNs) for controlling autonomous
cyber-physical systems (CPSs). One challenge with this approach is that many autonomous …

Although deep reinforcement learning (DRL) has many success stories, the large-scale
deployment of policies learned through these advanced techniques in safety-critical …

This paper investigates reinforcement learning with constraints, which are indispensable in
safety-critical environments. To drive the constraint violation to decrease monotonically, we …