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

We present a hierarchical planning and control framework that enables anagent to perform various tasks and adapt to a new task flexibly. Rather thanlearning an individual policy for each particular task, the proposed framework,DISH, distills a hierarchical policy from a set of tasks by representation andreinforcement learning. The framework is based on the idea of latent variablemodels that represent high-dimensional observations using low-dimensionallatent variables. The resulting policy consists of two levels of hierarchy: (i)a planning module that reasons a sequence of latent intentions that would leadto an optimistic future and (ii) a feedback control policy, shared across thetasks, that executes the inferred intention. Because the planning is performedin low-dimensional latent space, the learned policy can immediately be used tosolve or adapt to new tasks without additional training. We demonstrate theproposed framework can learn compact representations (3- and 1-dimensionallatent states and commands for a humanoid with 197- and 36-dimensional statefeatures and actions) while solving a small number of imitation tasks, and theresulting policy is directly applicable to other types of tasks, i.e.,navigation in cluttered environments. Video: https://youtu.be/HQsQysUWOhg

Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning