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

A variety of representation learning approaches have been investigated forreinforcement learning; much less attention, however, has been given toinvestigating the utility of sparse coding. Outside of reinforcement learning,sparse coding representations have been widely used, with non-convex objectivesthat result in discriminative representations. In this work, we develop asupervised sparse coding objective for policy evaluation. Despite thenon-convexity of this objective, we prove that all local minima are globalminima, making the approach amenable to simple optimization strategies. Weempirically show that it is key to use a supervised objective, rather than themore straightforward unsupervised sparse coding approach. We compare thelearned representations to a canonical fixed sparse representation, calledtile-coding, demonstrating that the sparse coding representation outperforms awide variety of tilecoding representations.

Learning Sparse Representations in Reinforcement Learning with Sparse Coding