Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
Glossop, Catherine R., Panerati, Jacopo, Krishnan, Amrit, Yuan, Zhaocong, Schoellig, Angela P.
–arXiv.org Artificial Intelligence
In this study, we leverage the deliberate and systematic fault-injection capabilities of an open-source benchmark suite to perform a series of experiments on state-of-the-art deep and robust reinforcement learning algorithms. We aim to benchmark robustness in the context of continuous action spaces -- crucial for deployment in robot control. We find that robustness is more prominent for action disturbances than it is for disturbances to observations and dynamics. We also observe that state-of-the-art approaches that are not explicitly designed to improve robustness perform at a level comparable to that achieved by those that are. Our study and results are intended to provide insight into the current state of safe and robust reinforcement learning and a foundation for the advancement of the field, in particular, for deployment in robotic systems.
arXiv.org Artificial Intelligence
Oct-27-2022
- Country:
- North America
- United States
- New York (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Canada > Ontario
- Toronto (0.28)
- United States
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Genre:
- Research Report > New Finding (0.88)
- Industry:
- Leisure & Entertainment (0.67)
- Education (0.46)
- Technology: