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

Learning a policy using only observational data is challenging because thedistribution of states it induces at execution time may differ from thedistribution observed during training. We propose to train a policy byunrolling a learned model of the environment dynamics over multiple time stepswhile explicitly penalizing two costs: the original cost the policy seeks tooptimize, and an uncertainty cost which represents its divergence from thestates it is trained on. We measure this second cost by using the uncertaintyof the dynamics model about its own predictions, using recent ideas fromuncertainty estimation for deep networks. We evaluate our approach using alarge-scale observational dataset of driving behavior recorded from trafficcameras, and show that we are able to learn effective driving policies frompurely observational data, with no environment interaction.

Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic