Examples or implementation details about Maximum Entropy Diverse Exploration in unity games

I am working on a research project on using ML algorithms to train agents in game developed using unity. I saw a blog "Discoverable Behavior Diversity" in the url "https://blog.unity.com/technology/u...elerating-learning-with-the-ml-agents-toolkit". it is about the implementation of Maximum Entropy Diverse Exploration. It will be helpful for me if I can get any examples of its implementation or the implementation details.