A Series of Unlikely Events: Learning Patterns by Observing Sequential Behavior (video)
November 2019 • Video
A Series of Unlikely Events: Learning Patterns by Observing Sequential Behavior
Software Engineering Institute
In this work, We propose an alternative approach, inverse reinforcement learning (IRL), that observes all states and actions in data and computes a statistical model of the world that includes whether each behavior is part of a routine. Deviations from routines have a low likelihood of
occurrence within the model.