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

There is a growing interest in developing automated agents that can workalongside humans. In addition to completing the assigned task, such an agentwill undoubtedly be expected to behave in a manner that is preferred by thehuman. This requires the human to communicate their preferences to the agent.To achieve this, the current approaches either require the users to specify thereward function or the preference is interactively learned from queries thatask the user to compare behavior. The former approach can be challenging if theinternal representation used by the agent is inscrutable to the human while thelatter is unnecessarily cumbersome for the user if their preference can bespecified more easily in symbolic terms. In this work, we propose PRESCA(PREference Specification through Concept Acquisition), a system that allowsusers to specify their preferences in terms of concepts that they understand.PRESCA maintains a set of such concepts in a shared vocabulary. If the relevantconcept is not in the shared vocabulary, then it is learned. To make learning anew concept more feedback efficient, PRESCA leverages causal associationsbetween the target concept and concepts that are already known. In addition, weuse a novel data augmentation approach to further reduce required feedback. Weevaluate PRESCA by using it on a Minecraft environment and show that it caneffectively align the agent with the user's preference.

Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion