深層強化学習による歩行スキル学習:行動空間の選択は重要か?
Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
歩行周期の模倣タスクにおいて、トルク・筋活性・関節角度・関節角速度という4種類の行動表現を比較し、高レベルな行動パラメータ化が学習効率やロバスト性、動作品質に大きく影響することを示した。
著者: Xue Bin Peng, Michiel van de Panne
分類: cs.LG, cs.GR, cs.RO
原文アブストラクト
The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance. We compare the impact of four different action parameterizations (torques, muscle-activations, target joint angles, and target joint-angle velocities) in terms of learning time, policy robustness, motion quality, and policy query rates. Our results are evaluated on a gait-cycle imitation task for multiple planar articulated figures and multiple gaits. We demonstrate that the local feedback provided by higher-level action parameterizations can significantly impact the learning, robustness, and quality of the resulting policies.
