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

Parameterized movement primitives have been extensively used for imitationlearning of robotic tasks. However, the high-dimensionality of the parameterspace hinders the improvement of such primitives in the reinforcement learning(RL) setting, especially for learning with physical robots. In this paper wepropose a novel view on handling the demonstrated trajectories for acquiringlow-dimensional, non-linear latent dynamics, using mixtures of probabilisticprincipal component analyzers (MPPCA) on the movements' parameter space.Moreover, we introduce a new contextual off-policy RL algorithm, namedLAtent-Movements Policy Optimization (LAMPO). LAMPO can provide gradientestimates from previous experience using self-normalized importance sampling,hence, making full use of samples collected in previous learning iterations.These advantages combined provide a complete framework for sample-efficientoff-policy optimization of movement primitives for robot learning ofhigh-dimensional manipulation skills. Our experimental results conducted bothin simulation and on a real robot show that LAMPO provides sample-efficientpolicies against common approaches in literature.

Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills