Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior

TL;DR

This paper reviews and organizes the diverse concepts related to making agent behavior understandable, predictable, and secure, highlighting overlaps and distinctions among these interrelated but sometimes conflicting notions.

Contribution

It provides a comprehensive taxonomy of key concepts like explicability, legibility, predictability, transparency, security, and privacy in interpretable agent behavior.

Findings

Clarifies the semantics and scope of each concept

Identifies overlaps and conflicts among different notions

Proposes a unified framework for understanding interpretable agent behavior

Abstract

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on "security" and "privacy" of plans which are also trying to answer the same question, but from the opposite point of view -- i.e. when the agent is trying to hide instead of revealing its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.