Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?Download PDF

28 Mar 2024 (modified: 21 Jul 2022)Submitted to ICLR 2017Readers: Everyone
Abstract: 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.
TL;DR: 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.
Conflicts: cs.ubc.ca
Keywords: Reinforcement Learning, Applications
12 Replies

Loading