In the dynamic and uncertain environments where reinforcement learning (...
This paper presents an approach for data-driven policy refinement in
rei...
In many real-world applications, safety constraints for reinforcement
le...
Simulation-based falsification is a practical testing method to increase...
Compared with model-based control and optimization methods, reinforcemen...
Many approaches for scalable GPs have focused on using a subset of data ...
We present a safety verification framework for design-time and run-time
...
We propose a general framework for creating parameterized control scheme...
In this paper, we present a safe deep reinforcement learning system for
...