Skip to main content

Alternating Optimisation and Quadrature for Robust Control

Supratik Paul‚ Konstantinos Chatzilygeroudis‚ Kamil Ciosek‚ Jean−Baptiste Mouret‚ Michael Osborne and Shimon Whiteson

Abstract

Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), which uses Bayesian optimisation and Bayesian quadrature to address such settings. ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy. Experimental results across different domains show that ALOQ can learn more efficiently and robustly than existing methods.

Book Title
AAAI 2018: Proceedings of the Thirty−Second AAAI Conference on Artificial Intelligence
Month
February
Note
To appear.
Year
2018