search menu icon-carat-right cmu-wordmark

Poster - A Series of Unlikely Events

November 2020 Poster
Eric Heim

The poster summarizes learning from sequential behavior for activity-based intelligence and modeling human expertise.

Publisher:

Software Engineering Institute

Abstract

Modeling patterns of sequential behavior is a task that underlies numerous difficult artificial intelligence tasks. Imitation Learning (IL) techniques are an efficient and effective means to perform activity-based intelligence or to help automate the education of novices on how to perform tasks like experts. The goals of this work are to investigate the practicality of applying IL to behavioral modeling problems; apply IL techniques to DoD/IC relevant problems; and develop techniques that are able to explain, simulate, and demonstrate expert behavior.