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

In dynamic motion generation tasks, including contact and collisions, smallchanges in policy parameters can lead to extremely different returns. Forexample, in soccer, the ball can fly in completely different directions with asimilar heading motion by slightly changing the hitting position or the forceapplied to the ball or when the friction of the ball varies. However, it isdifficult to imagine that completely different skills are needed for heading aball in different directions. In this study, we proposed a multitaskreinforcement learning algorithm for adapting a policy to implicit changes ingoals or environments in a single motion category with different rewardfunctions or physical parameters of the environment. We evaluated the proposedmethod on the ball heading task using a monopod robot model. The results showedthat the proposed method can adapt to implicit changes in the goal positions orthe coefficients of restitution of the ball, whereas the standard domainrandomization approach cannot cope with different task settings.

A Policy Adaptation Method for Implicit Multitask Reinforcement Learning Problems