Operational Feel Adjustment for Power-Assisted Positioning by an Actor-Critic Method

Abstract

This paper proposes a method of operational feel adjustment using reinforcement learning for power-assisted positioning. To illustrate difference from the author's previous study and motivation of the study in this paper, two methods of reinforcement learning, Sarsa and actor-critic methods, are experimentally compared at first with a simple example. Then, operational feel adjustment using an actor-critic method is proposed and examined by experiment. Results obtained in experiment are observed for some discussion, and concluding remark makes mention of some future issues.