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

In this paper, we show how novel transfer reinforcement learning techniquescan be applied to the complex task of target driven navigation using thephotorealistic AI2THOR simulator. Specifically, we build on the concept ofUniversal Successor Features with an A3C agent. We introduce the novelarchitectural contribution of a Successor Feature Dependant Policy (SFDP) andadopt the concept of Variational Information Bottlenecks to achieve state ofthe art performance. VUSFA, our final architecture, is a straightforwardapproach that can be implemented using our open source repository. Our approachis generalizable, showed greater stability in training, and outperformed recentapproaches in terms of transfer learning ability.

VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation