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

Providing explanations is considered an imperative ability for an AI agent ina human-robot teaming framework. The right explanation provides the rationalebehind an AI agent's decision-making. However, to maintain the human teammate'scognitive demand to comprehend the provided explanations, prior works havefocused on providing explanations in a specific order or intertwining theexplanation generation with plan execution. Moreover, these approaches do notconsider the degree of details required to share throughout the providedexplanations. In this work, we argue that the agent-generated explanations,especially the complex ones, should be abstracted to be aligned with the levelof details the human teammate desires to maintain the recipient's cognitiveload. Therefore, learning a hierarchical explanations model is a challengingtask. Moreover, the agent needs to follow a consistent high-level policy totransfer the learned teammate preferences to a new scenario while lower-leveldetailed plans are different. Our evaluation confirmed the process ofunderstanding an explanation, especially a complex and detailed explanation, ishierarchical. The human preference that reflected this aspect correspondedexactly to creating and employing abstraction for knowledge assimilation hiddendeeper in our cognitive process. We showed that hierarchical explanationsachieved better task performance and behavior interpretability while reducedcognitive load. These results shed light on designing explainable agentsutilizing reinforcement learning and planning across various domains.

Are We On The Same Page? Hierarchical Explanation Generation for Planning Tasks in Human-Robot Teaming using Reinforcement Learning