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

Model-based reinforcement learning is a widely accepted solution for solvingexcessive sample demands. However, the predictions of the dynamics models areoften not accurate enough, and the resulting bias may incur catastrophicdecisions due to insufficient robustness. Therefore, it is highly desired toinvestigate how to improve the robustness of model-based RL algorithms whilemaintaining high sampling efficiency. In this paper, we propose Model-BasedDouble-dropout Planning (MBDP) to balance robustness and efficiency. MBDPconsists of two kinds of dropout mechanisms, where the rollout-dropout aims toimprove the robustness with a small cost of sample efficiency, while themodel-dropout is designed to compensate for the lost efficiency at a slightexpense of robustness. By combining them in a complementary way, MBDP providesa flexible control mechanism to meet different demands of robustness andefficiency by tuning two corresponding dropout ratios. The effectiveness ofMBDP is demonstrated both theoretically and experimentally.

MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning