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

Value alignment is a property of an intelligent agent indicating that it canonly pursue goals and activities that are beneficial to humans. Traditionalapproaches to value alignment use imitation learning or preference learning toinfer the values of humans by observing their behavior. We introduce acomplementary technique in which a value aligned prior is learned fromnaturally occurring stories which encode societal norms. Training data issourced from the childrens educational comic strip, Goofus and Gallant. In thiswork, we train multiple machine learning models to classify natural languagedescriptions of situations found in the comic strip as normative or nonnormative by identifying if they align with the main characters behavior. Wealso report the models performance when transferring to two unrelated taskswith little to no additional training on the new task.

Learning Norms from Stories: A Prior for Value Aligned Agents