Back to Search
Start Over
SAMBA: Safe Model-Based & Active Reinforcement Learning
- Publication Year :
- 2020
-
Abstract
- In this paper, we propose SAMBA, a novel framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. Our method builds upon PILCO to enable active exploration using novel(semi-)metrics for out-of-sample Gaussian process evaluation optimised through a multi-objective problem that supports conditional-value-at-risk constraints. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. Our results show orders of magnitude reductions in samples and violations compared to state-of-the-art methods. Lastly, we provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2006.09436
- Document Type :
- Working Paper