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

Standard reinforcement learning methods aim to master one way of solving atask whereas there may exist multiple near-optimal policies. Being able toidentify this collection of near-optimal policies can allow a domain expert toefficiently explore the space of reasonable solutions. Unfortunately, existingapproaches that quantify uncertainty over policies are not ultimately relevantto finding policies with qualitatively distinct behaviors. In this work, weformalize the difference between policies as a difference between thedistribution of trajectories induced by each policy, which encourages diversitywith respect to both state visitation and action choices. We derive agradient-based optimization technique that can be combined with existing policygradient methods to now identify diverse collections of well-performingpolicies. We demonstrate our approach on benchmarks and a healthcare task.

Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies