Reinforcement Learning Algorithms in Global Path Planning for Mobile Robot

Abstract

The paper is devoted to the research of two approaches for global path planning for mobile robots, based on Q-Learning and Sarsa algorithms. The study has been done with different adjustments of two algorithms that made it possible to learn faster. The implementation of two Reinforcement Learning algorithms showed differences in learning time and the methods of building path to avoid obstacles and to reach a destination point. The analysis of obtained results made it possible to select optimal parameters of the considered algorithms for the tested environments. Experiments were performed in virtual environments where algorithms learned which steps to choose in order to get a maximum payoff and reach the goal avoiding obstacles.