Method for controlling a laser processing operation by means of a reinforcement learning agent and laser material processing head using the same

Method for controlling a processing operation of a workpiece by means of a Reinforcement Learning (RL) agent unit, comprising the steps of:

• (a) observing an interaction zone in the workpiece by means of at least one radiation sensor to generate at least one sensor signal st;
• wherein the workpiece is processed using an actuator having an initial actuator value at;
• (b) determining a basis function φ(st) from the set of sensor signals st;
• (c) determining a reward function rt giving the probability of good results of the processing operation;
• (d) choosing a next actuator value at+1 on the basis of a policy π depending on the reward function rt and the basis function φ(st);
• and
• (e) repeating the steps (a) to (d) for further time points to perform an R L controlled processing operation, and wherein steps (a) and (b) comprise the steps of:
• recording a pixel image at an initial time point of an interaction zone in the workpiece by means of a camera, wherein the workpiece is processed using an actuator having an initial actuator value at;
• converting the pixel image into a pixel vector st;
• and
• representing the pixel vector st by a sum of predetermined pixel mappings each multiplied by a corresponding feature value, wherein the set of feature values φ(st) represents the basis function φ(st).