Titlebook: Explainable Human-AI Interaction; A Planning Perspecti Sarath Sreedharan,Anagha Kulkarni,Subbarao Kambham Book 2022 Springer Nature Switzer

harpsichord

Applications,ome up with decisions for a specific task and another system designed for helping users specify a declarative model of task (specifically in the context of dialogue planning for an enterprise chat agent).

BRACE

ABOUT

https://doi.org/10.1007/978-3-030-23645-8otations in place, we will then focus on establishing the three main interpretability measures in human-aware planning; namely, . We will revisit two of these measures (i.e., explicability and legibility) and discuss methods to boost these measures throughout the later chapters.

Landlocked

Obsessed

暫停,間歇

emulsify

Introduction,rn anywhere without running into mentions of AI technology and hype about its expected positive and negative societal impacts. AI has been compared to fire . electricity, and commercial interest in the AI technologies has sky rocketed. Universities—even high schools—are rushing to start new degree p

Chandelier

Measures of Interpretability,will use, including the definitions of deterministic goal-directed planning problems, incomplete planning models, sensor models, etc. With the basic notations in place, we will then focus on establishing the three main interpretability measures in human-aware planning; namely, . We will revisit two

FIN

Explicable Behavior Generation,s chapter, we will take a closer look at explicability and discuss some practical methods to facilitate explicable planning. This would include discussion on both planning algorithms specifically designed for generating explicable behavior and how one could design/update the task to make the generat

Carcinogenesis

Legible Behavior,implicitly communicate information about its goals, plans (or model, in general) to a human observer. For instance, consider a human robot cohabitation scenario consisting of a multi-tasking robot with varied capabilities that is capable of performing a multitude of tasks in an environment. In such