不完全な実演の敵対的模倣による俊敏スキルの学習
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
物理的に不完全な部分実演からWasserstein GANで報酬を推定し、四足ロボットSolo 8でバク宙などの俊敏スキルを獲得する手法を提案。
著者: Chenhao Li, Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger, Georg Martius
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Learning agile skills is one of the main challenges in robotics. To this end, reinforcement learning approaches have achieved impressive results. These methods require explicit task information in terms of a reward function or an expert that can be queried in simulation to provide a target control output, which limits their applicability. In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible. Moreover, we show that by using a Wasserstein GAN formulation and transitions from demonstrations with rough and partial information as input, we are able to extract policies that are robust and capable of imitating demonstrated behaviors. Finally, the obtained skills such as a backflip are tested on an agile quadruped robot called Solo 8 and present faithful replication of hand-held human demonstrations.
