Reinforcement learning approach to generate goal-directed locomotion of a snake-like robot with screw-drive units

In this paper we apply a policy improvement algorithm called Policy Improvement with Path Integrals (PI²) to generate goal-directed locomotion of a complex snake-like robot with screw-drive units. PI² is numerically simple and has an ability to deal with high dimensional systems. Here, this approach is used to find proper locomotion control parameters, like joint angles and screw-drive velocities, of the robot. The learning process was achieved using a simulated robot and the learned parameters were successfully transferred to the real one. As a result the robot can locomote toward a given goal.