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

Monte Carlo methods have become increasingly relevant for control ofnon-differentiable systems, approximate dynamics models and learning from data.These methods scale to high-dimensional spaces and are effective at thenon-convex optimizations often seen in robot learning. We look at sample-basedmethods from the perspective of inference-based control, specifically posteriorpolicy iteration. From this perspective, we highlight how Gaussian noise priorsproduce rough control actions that are unsuitable for physical robotdeployment. Considering smoother Gaussian process priors, as used in episodicreinforcement learning and motion planning, we demonstrate how smoother modelpredictive control can be achieved using online sequential inference. Thisinference is realized through an efficient factorization of the actiondistribution and a novel means of optimizing the likelihood temperature toimprove importance sampling accuracy. We evaluate this approach on severalhigh-dimensional robot control tasks, matching the sample efficiency of priorheuristic methods while also ensuring smoothness. Simulation results can beseen at https://monte-carlo-ppi.github.io/.

Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes