Predicting Trajectories with Directed-Info GAIL

Summary

As it is well known from works on imitation learning methods, the use of imitation learning to learn a single policy for a complex task that has multiple modes or hierarchical structure can be  challenging. This thesis explores the use of Directed-Info GAIL algorithm, which is  based on the generative adversarial imitation learning framework, to automatically learn subtask policies from unsegmented demonstrations of robot trajectories and aircraft trajectories, given that flights and robots have indeed different modes of behaviour in different segments of trajectories, depending on tasks they fulfil, trajectories' contextual features and agents’- executing these tasks- preferences.