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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Explainable reinforcement learning allows artificial agents to explain theirbehavior in a human-like manner aiming at non-expert end-users. An efficientalternative of creating explanations is to use an introspection-based methodthat transforms Q-values into probabilities of success used as the base toexplain the agent's decision-making process. This approach has been effectivelyused in episodic and discrete scenarios, however, to compute the probability ofsuccess in non-episodic and more complex environments has not been addressedyet. In this work, we adapt the introspection method to be used in anon-episodic task and try it in a continuous Atari game scenario solved withthe Rainbow algorithm. Our initial results show that the probability of successcan be computed directly from the Q-values for all possible actions.

Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task