An RLS-Based Natural Actor-Critic Algorithm for Locomotion of a Two-Linked Robot Arm

Recently, actor-critic methods have drawn much interests in the area of reinforcement learning, and several algorithms have been studied along the line of the actor-critic strategy. This paper studies an actor-critic type algorithm utilizing the RLS(recursive least-squares) method, which is one of the most efficient techniques for adaptive signal processing, together with natural policy gradient. In the actor part of the studied algorithm, we follow the strategy of performing parameter update via the natural gradient method, while in its update for the critic part, the recursive least-squares method is employed in order to make the parameter estimation for the value functions more efficient. The studied algorithm was applied to locomotion of a two-linked robot arm, and showed better performance compared to the conventional stochastic gradient ascent algorithm.