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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Legged locomotion is a challenging task for learning algorithms, especiallywhen the task requires a diverse set of primitive behaviors. To solve theseproblems, we introduce a hierarchical framework to automatically decomposecomplex locomotion tasks. A high-level policy issues commands in a latent spaceand also selects for how long the low-level policy will execute the latentcommand. Concurrently, the low-level policy uses the latent command and onlythe robot's on-board sensors to control the robot's actuators. Our approachallows the high-level policy to run at a lower frequency than the low-levelone. We test our framework on a path-following task for a dynamic quadrupedrobot and we show that steering behaviors automatically emerge in the latentcommand space as low-level skills are needed for this task. We then showefficient adaptation of the trained policy to a different task by transfer ofthe trained low-level policy. Finally, we validate the policies on a realquadruped robot. To the best of our knowledge, this is the first application ofend-to-end hierarchical learning to a real robotic locomotion task.

Hierarchical Reinforcement Learning for Quadruped Locomotion