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

Mutual information-based reinforcement learning (RL) has been proposed as apromising framework for retrieving complex skills autonomously without atask-oriented reward function through mutual information (MI) maximization orvariational empowerment. However, learning complex skills is still challenging,due to the fact that the order of training skills can largely affect sampleefficiency. Inspired by this, we recast variational empowerment as curriculumlearning in goal-conditioned RL with an intrinsic reward function, which wename Variational Curriculum RL (VCRL). From this perspective, we propose anovel approach to unsupervised skill discovery based on information theory,called Value Uncertainty Variational Curriculum (VUVC). We prove that, underregularity conditions, VUVC accelerates the increase of entropy in the visitedstates compared to the uniform curriculum. We validate the effectiveness of ourapproach on complex navigation and robotic manipulation tasks in terms ofsample efficiency and state coverage speed. We also demonstrate that the skillsdiscovered by our method successfully complete a real-world robot navigationtask in a zero-shot setup and that incorporating these skills with a globalplanner further increases the performance.

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills