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

Although exploration in reinforcement learning is well understood from atheoretical point of view, provably correct methods remain impractical. In thispaper we study the interplay between exploration and approximation, what wecall approximate exploration. Our main goal is to further our theoreticalunderstanding of pseudo-count based exploration bonuses (Bellemare et al.,2016), a practical exploration scheme based on density modelling. As a warm-up,we quantify the performance of an exploration algorithm, MBIE-EB (Strehl andLittman, 2008), when explicitly combined with state aggregation. This allows usto confirm that, as might be expected, approximation allows the agent to tradeoff between learning speed and quality of the learned policy. Next, we show howa given density model can be related to an abstraction and that thecorresponding pseudo-count bonus can act as a substitute in MBIE-EB combinedwith this abstraction, but may lead to either under- or over-exploration. Then,we show that a given density model also defines an implicit abstraction, andfind a surprising mismatch between pseudo-counts derived either implicitly orexplicitly. Finally we derive a new pseudo-count bonus alleviating this issue.

Approximate Exploration through State Abstraction