English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sample-based trajectory optimisers are a promising tool for the control ofrobotics with non-differentiable dynamics and cost functions. Contemporaryapproaches derive from a restricted subclass of stochastic optimal controlwhere the optimal policy can be expressed in terms of an expectation overstochastic paths. By estimating the expectation with Monte Carlo sampling andreinterpreting the process as exploration noise, a stochastic search algorithmis obtained tailored to (deterministic) trajectory optimisation. For thepurpose of future algorithmic development, it is essential to properlyunderstand the underlying theoretical foundations that allow for a principledderivation of such methods. In this paper we make a connection between entropyregularisation in optimisation and deterministic optimal control. We then showthat the optimal policy is given by a belief function rather than adeterministic function. The policy belief is governed by a Bayesian-type updatewhere the likelihood can be expressed in terms of a conditional expectationover paths induced by a prior policy. Our theoretical investigation firmlyroots sample based trajectory optimisation in the larger family of control asinference. It allows us to justify a number of heuristics that are common inthe literature and motivate a number of new improvements that benefitconvergence.

Entropy Regularised Deterministic Optimal Control: From Path Integral Solution to Sample-Based Trajectory Optimisation