Skip to yearly menu bar Skip to main content


Imitating Latent Policies from Observation

Ashley Edwards · Himanshu Sahni · Yannick Schroecker · Charles Isbell

Pacific Ballroom #33

Keywords: [ Deep Reinforcement Learning ]


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

Live content is unavailable. Log in and register to view live content