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

We are motivated by the problem of learning policies for robotic systems withrich sensory inputs (e.g., vision) in a manner that allows us to guaranteegeneralization to environments unseen during training. We provide a frameworkfor providing such generalization guarantees by leveraging a finite dataset ofreal-world environments in combination with a (potentially inaccurate)generative model of environments. The key idea behind our approach is toutilize the generative model in order to implicitly specify a prior overpolicies. This prior is updated using the real-world dataset of environments byminimizing an upper bound on the expected cost across novel environmentsderived via Probably Approximately Correct (PAC)-Bayes generalization theory.We demonstrate our approach on two simulated systems with nonlinear/hybriddynamics and rich sensing modalities: (i) quadrotor navigation with an onboardvision sensor, and (ii) grasping objects using a depth sensor. Comparisons withprior work demonstrate the ability of our approach to obtain strongergeneralization guarantees by utilizing generative models. We also presenthardware experiments for validating our bounds for the grasping task.

Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data