敵対的学習による俊敏な歩行の獲得
Learning Agile Locomotion via Adversarial Training
四足ロボットが追跡者、別のロボットが逃走者となって敵対的に学習することで、環境設計の手間を減らしつつ俊敏な歩行制御を自動獲得する手法を提案。
著者: Yujin Tang, Jie Tan, Tatsuya Harada
分類: cs.RO, cs.AI
原文アブストラクト
Developing controllers for agile locomotion is a long-standing challenge for legged robots. Reinforcement learning (RL) and Evolution Strategy (ES) hold the promise of automating the design process of such controllers. However, dedicated and careful human effort is required to design training environments to promote agility. In this paper, we present a multi-agent learning system, in which a quadruped robot (protagonist) learns to chase another robot (adversary) while the latter learns to escape. We find that this adversarial training process not only encourages agile behaviors but also effectively alleviates the laborious environment design effort. In contrast to prior works that used only one adversary, we find that training an ensemble of adversaries, each of which specializes in a different escaping strategy, is essential for the protagonist to master agility. Through extensive experiments, we show that the locomotion controller learned with adversarial training significantly outperforms carefully designed baselines.
