A METHOD AND A SYSTEM FOR APPLYING MACHINE LEARNING TO AN APPLICATION

摘要

A method for applying machine learning, in particular state based machine learning, to an application, comprising the steps: a) Generating a candidate policy (P) by a learner (20); b) Executing a program (80) in at least one simulated application (51, 52) based on a set of candidate parameters (PC1, PC2) provided based on the candidate policy (P) and a state (S) of the simulated application (51, 52), the execution of the program providing interim results (R1, R2) of tested sets of candidate parameters (PC1, PC2) based on a measured performance information of the execution of the program (80); c) Collecting a predetermined number of interim results (R1, R2) and providing an end result (R) based on a combination of the candidate parameters (PC) and/or the state (S) with the measured performances information by a trainer (30); and d) Generating a new candidate policy (P) by the learner (20) based on the end result (R).