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

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