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

Humans are capable of abstracting various tasks as different combinations ofmultiple attributes. This perspective of compositionality is vital for humanrapid learning and adaption since previous experiences from related tasks canbe combined to generalize across novel compositional settings. In this work, weaim to achieve zero-shot policy generalization of Reinforcement Learning (RL)agents by leveraging the task compositionality. Our proposed method is a meta-RL algorithm with disentangled task representation, explicitly encodingdifferent aspects of the tasks. Policy generalization is then performed byinferring unseen compositional task representations via the obtaineddisentanglement without extra exploration. The evaluation is conducted on threesimulated tasks and a challenging real-world robotic insertion task.Experimental results demonstrate that our proposed method achieves policygeneralization to unseen compositional tasks in a zero-shot manner.

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning