Alternating Optimisation and Quadrature for Robust Control

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.
Type de document :
Communication dans un congrès
AAAI 2018 - The Thirty-Second AAAI Conference on Artificial Intelligence, Feb 2018, New Orleans, United States
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01644063
Contributeur : Jean-Baptiste Mouret <>
Soumis le : mercredi 22 novembre 2017 - 11:16:41
Dernière modification le : jeudi 11 janvier 2018 - 06:27:29

Fichier

ALOQ_AAAI18_final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

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

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〉

Partager

Métriques

Consultations de la notice

257

Téléchargements de fichiers

166