Alternating Optimisation and Quadrature for Robust Control

Supratik Paul 1 Konstantinos Chatzilygeroudis 2 Kamil Ciosek 1 Jean-Baptiste Mouret 2 Michael Osborne 1 Shimon Whiteson 1
1 University of Oxford [Oxford]
2 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [27 references]  Display  Hide  Download
https://hal.inria.fr/hal-01644063
Contributor : Jean-Baptiste Mouret <>
Submitted on : Wednesday, November 22, 2017 - 11:16:41 AM
Last modification on : Tuesday, December 18, 2018 - 4:40:22 PM

File

ALOQ_AAAI18_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01644063, version 1
  • ARXIV : 1605.07496

Collections

TDS-MACS | INRIA | LORIA | LORIA-AIS | UNIV-LORRAINE

Citation

Supratik Paul, Konstantinos Chatzilygeroudis, Kamil Ciosek, Jean-Baptiste Mouret, Michael 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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

350

Files downloads

195

Contact


archive-ouverte@inria.fr