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

Simulation provides a safe and efficient way to generate useful data forlearning complex robotic tasks. However, matching simulation and real-worlddynamics can be quite challenging, especially for systems that have a largenumber of unobserved or unmeasurable parameters, which may lie in the robotdynamics itself or in the environment with which the robot interacts. Weintroduce a novel approach to tackle such a sim-to-real problem by developingpolicies capable of adapting to new environments, in a zero-shot manner. Key toour approach is an error-aware policy (EAP) that is explicitly made aware ofthe effect of unobservable factors during training. An EAP takes as input thepredicted future state error in the target environment, which is provided by anerror-prediction function, simultaneously trained with the EAP. We validate ourapproach on an assistive walking device trained to help the human user recoverfrom external pushes. We show that a trained EAP for a hip-torque assistivedevice can be transferred to different human agents with unseen biomechanicalcharacteristics. In addition, we show that our method can be applied to otherstandard RL control tasks.

Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments