Edinburgh Research Archive logo

Edinburgh Research Archive

University of Edinburgh homecrest
View Item 
  •   ERA Home
  • Informatics, School of
  • Informatics thesis and dissertation collection
  • View Item
  •   ERA Home
  • Informatics, School of
  • Informatics thesis and dissertation collection
  • View Item
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.

On probabilistic inference approaches to stochastic optimal control

View/Open
sources.zip (3.344Mb)
Rawlik2013.pdf (2.664Mb)
Date
28/11/2013
Author
Rawlik, Konrad Cyrus
Metadata
Show full item record
Abstract
While stochastic optimal control, together with associate formulations like Reinforcement Learning, provides a formal approach to, amongst other, motor control, it remains computationally challenging for most practical problems. This thesis is concerned with the study of relations between stochastic optimal control and probabilistic inference. Such dualities { exempli ed by the classical Kalman Duality between the Linear-Quadratic-Gaussian control problem and the filtering problem in Linear-Gaussian dynamical systems { make it possible to exploit advances made within the separate fields. In this context, the emphasis in this work lies with utilisation of approximate inference methods for the control problem. Rather then concentrating on special cases which yield analytical inference problems, we propose a novel interpretation of stochastic optimal control in the general case in terms of minimisation of certain Kullback-Leibler divergences. Although these minimisations remain analytically intractable, we show that natural relaxations of the exact dual lead to new practical approaches. We introduce two particular general iterative methods ψ-Learning, which has global convergence guarantees and provides a unifying perspective on several previously proposed algorithms, and Posterior Policy Iteration, which allows direct application of inference methods. From these, practical algorithms for Reinforcement Learning, based on a Monte Carlo approximation to ψ-Learning, and model based stochastic optimal control, using a variational approximation of posterior policy iteration, are derived. In order to overcome the inherent limitations of parametric variational approximations, we furthermore introduce a new approach for none parametric approximate stochastic optimal control based on a reproducing kernel Hilbert space embedding of the control problem. Finally, we address the general problem of temporal optimisation, i.e., joint optimisation of controls and temporal aspects, e.g., duration, of the task. Specifically, we introduce a formulation of temporal optimisation based on a generalised form of the finite horizon problem. Importantly, we show that the generalised problem has a dual finite horizon problem of the standard form, thus bringing temporal optimisation within the reach of most commonly used algorithms. Throughout, problems from the area of motor control of robotic systems are used to evaluate the proposed methods and demonstrate their practical utility.
URI
http://hdl.handle.net/1842/8293
Collections
  • Informatics thesis and dissertation collection

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page

 

 

All of ERACommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisorsThis CollectionBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisors
LoginRegister

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page