ラベルなし混合動作の自己教師あり敵対的模倣による多様なスキル制御
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
ラベルなしの多様な動作データから、敵対的模倣学習と教師なしスキル発見を組み合わせて、制御可能なスキルセットを持つ汎用方策を獲得する手法を提案し、四足ロボットSolo 8で実証した。
著者: Chenhao Li, Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey, Georg Martius
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable 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.
