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

Trading off exploration and exploitation in an unknown environment is key tomaximising expected return during learning. A Bayes-optimal policy, which doesso optimally, conditions its actions not only on the environment state but onthe agent's uncertainty about the environment. Computing a Bayes-optimal policyis however intractable for all but the smallest tasks. In this paper, weintroduce variational Bayes-Adaptive Deep RL (variBAD), a way to meta-learn toperform approximate inference in an unknown environment, and incorporate taskuncertainty directly during action selection. In a grid-world domain, weillustrate how variBAD performs structured online exploration as a function oftask uncertainty. We further evaluate variBAD on MuJoCo domains widely used inmeta-RL and show that it achieves higher online return than existing methods.

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning