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

Machine Learning models become increasingly proficient in complex tasks.However, even for experts in the field, it can be difficult to understand whatthe model learned. This hampers trust and acceptance, and it obstructs thepossibility to correct the model. There is therefore a need for transparency ofmachine learning models. The development of transparent classification modelshas received much attention, but there are few developments for achievingtransparent Reinforcement Learning (RL) models. In this study we propose amethod that enables a RL agent to explain its behavior in terms of the expectedconsequences of state transitions and outcomes. First, we define a translationof states and actions to a description that is easier to understand for humanusers. Second, we developed a procedure that enables the agent to obtain theconsequences of a single action, as well as its entire policy. The methodcalculates contrasts between the consequences of a policy derived from a userquery, and of the learned policy of the agent. Third, a format for generatingexplanations was constructed. A pilot survey study was conducted to explorepreferences of users for different explanation properties. Results indicatethat human users tend to favor explanations about policy rather than aboutsingle actions.

Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences