Reinforcement learning techniques applied to the motion planning of a robotic manipulator

Throughout this article the execution of the motion planning for a robotic manipulator by means of Reinforcement Learning methods is studied. Towards this, an implementation based on a “Wire and loop” game is used as an example case to be solved. The loop is controlled in a single plane as the end-effector of the manipulator. The modeling of the problem and the process of training the agent is detailed. This allowed for the verification of the capacity of a learning based method, having produced, under the considered abstractions, satisfying results by gaining the capability of completing the path imposed by the wire in 23 seconds.