Hey everyone, I have been learning RASA for a few weeks. Recently I am trying to read the RASA source code, but I found it hard for me to understand how RASA generate training data to train a Policy, I know the training data for Policy is generated in ‘TrainingDataGenerator._generate’, this method accept a list of StoryStep, and trying to construct the tracker states, it contains 200+ lines of code, I want to known is there any document to help me understand the logic behind it?
Rasa Version : 2.3.4
Rasa SDK Version : 2.4.0
Rasa X Version : None
Python Version : 3.7.5
Operating System : Darwin-19.6.0-x86_64-i386-64bit