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

Recurrent neural networks (RNNs) are an effective representation of controlpolicies for a wide range of reinforcement and imitation learning problems. RNNpolicies, however, are particularly difficult to explain, understand, andanalyze due to their use of continuous-valued memory vectors and observationfeatures. In this paper, we introduce a new technique, Quantized BottleneckInsertion, to learn finite representations of these vectors and features. Theresult is a quantized representation of the RNN that can be analyzed to improveour understanding of memory use and general behavior. We present results ofthis approach on synthetic environments and six Atari games. The resultingfinite representations are surprisingly small in some cases, using as few as 3discrete memory states and 10 observations for a perfect Pong policy. We alsoshow that these finite policy representations lead to improvedinterpretability.

Learning Finite State Representations of Recurrent Policy Networks