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

For robots operating in the real world, it is desirable to learn reusablebehaviours that can effectively be transferred and adapted to numerous tasksand scenarios. We propose an approach to learn abstract motor skills from datausing a hierarchical mixture latent variable model. In contrast to existingwork, our method exploits a three-level hierarchy of both discrete andcontinuous latent variables, to capture a set of high-level behaviours whileallowing for variance in how they are executed. We demonstrate in manipulationdomains that the method can effectively cluster offline data into distinct,executable behaviours, while retaining the flexibility of a continuous latentvariable model. The resulting skills can be transferred and fine-tuned on newtasks, unseen objects, and from state to vision-based policies, yielding bettersample efficiency and asymptotic performance compared to existing skill- andimitation-based methods. We further analyse how and when the skills are mostbeneficial: they encourage directed exploration to cover large regions of thestate space relevant to the task, making them most effective in challengingsparse-reward settings.

Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies