Reinforcement learning of walking behavior for a four-legged robot
Hajime Kimura, Toru Yamashita, S. Kobayashi · Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228) · 2003
In this paper, we investigate a reinforcement learning of walking behavior for a four-legged robot. The robot has two servo motors per leg, so this problem has eight-dimensional continuous state/action space. We present an action selection scheme for actor-critic algorithms, in which the actor selects a continuous action from its bounded action space by using the normal distribution. The experimental results show the robot successfully learns to walk in practical learning steps.