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

Learning agile skills is one of the main challenges in robotics. To this end,reinforcement learning approaches have achieved impressive results. Thesemethods require explicit task information in terms of a reward function or anexpert that can be queried in simulation to provide a target control output,which limits their applicability. In this work, we propose a generativeadversarial method for inferring reward functions from partial and potentiallyphysically incompatible demonstrations for successful skill acquirement wherereference or expert demonstrations are not easily accessible. Moreover, we showthat by using a Wasserstein GAN formulation and transitions from demonstrationswith rough and partial information as input, we are able to extract policiesthat are robust and capable of imitating demonstrated behaviors. Finally, theobtained skills such as a backflip are tested on an agile quadruped robotcalled Solo 8 and present faithful replication of hand-held humandemonstrations.

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations