Back to Search
Start Over
Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
- Publication Year :
- 2022
-
Abstract
- 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.<br />Comment: 18 pages, 15 figures
- Subjects :
- Computer Science - Robotics
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2210.15199
- Document Type :
- Working Paper