Alternating Optimisation and Quadrature for Robust Control - Archive ouverte HAL Access content directly
Conference Papers Year :

Alternating Optimisation and Quadrature for Robust Control

(1) , (2) , (1) , (2) , (1) , (1)
1
2

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 randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding an optimal 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 have a considerable impact on determining the optimal policy. We provide experimental results demonstrating our approach learning more efficiently than existing methods.
Fichier principal
Vignette du fichier
ALOQ_AAAI18_final.pdf (574.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01644063 , version 1 (22-11-2017)

Identifiers

Cite

Supratik Paul, Konstantinos Chatzilygeroudis, Kamil Ciosek, Jean-Baptiste Mouret, Michael A Osborne, et al.. Alternating Optimisation and Quadrature for Robust Control. AAAI 2018 - The Thirty-Second AAAI Conference on Artificial Intelligence, Feb 2018, New Orleans, United States. ⟨hal-01644063⟩
282 View
200 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More