Versatile Skill Control Via Self-Supervised Adversarial Imitation of Unlabeled Mixed Motions

Learning diverse skills is one of the main chal- lenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explic- itly labeled datasets or assume consistent skill execution to en- able learning and active control of individual behaviors, which limits their applicability. In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. Moreover, we show that by utilizing unsupervised skill discovery in the generative adversarial imitation learning framework, novel and useful skills emerge with successful task fulfillment. Finally, the obtained versatile policies are tested on an agile quadruped robot called Solo 8 and present faithful replications of diverse skills encoded in the demonstrations.