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

We tackle the blackbox issue of deep neural networks in the settings ofreinforcement learning (RL) where neural agents learn towards maximizing rewardgains in an uncontrollable way. Such learning approach is risky when theinteracting environment includes an expanse of state space because it is thenalmost impossible to foresee all unwanted outcomes and penalize them withnegative rewards beforehand. Unlike reverse analysis of learned neural featuresfrom previous works, our proposed method \nj{tackles the blackbox issue byencouraging} an RL policy network to learn interpretable latent featuresthrough an implementation of a disentangled representation learning method.Toward this end, our method allows an RL agent to understand self-efficacy bydistinguishing its influences from uncontrollable environmental factors, whichclosely resembles the way humans understand their scenes. Our experimentalresults show that the learned latent factors not only are interpretable, butalso enable modeling the distribution of entire visited state space with aspecific action condition. We have experimented that this characteristic of theproposed structure can lead to ex post facto governance for desired behaviorsof RL agents.

Towards Governing Agent's Efficacy: Action-Conditional $\beta$-VAE for Deep Transparent Reinforcement Learning