In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between the latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within classic control environments and a platform game and demonstrate that it performs better than standard approaches. Code for this work is available at https://github.com/ashedwards/ILPO.
Ashley Edwards (Georgia Institute of Technology)
Himanshu Sahni (Georgia Institute of Technology)
Yannick Schroecker (Georgia Institute of Technology)
Charles Isbell (Georgia Institute of Technology)
Related Events (a corresponding poster, oral, or spotlight)
2019 Oral: Imitating Latent Policies from Observation »
Wed Jun 12th 11:25 -- 11:30 AM Room Hall B