Self play in ml agent

[strong trench]

Is there any official tutorial on unity ml agent Record demonstrations?

and I have a question is it really like a RLHF ? if not what are the technical differences ?

I found this via gothub link idk why itis unlisted ut this what I meant https://www.youtube.com/watch?v=kpb8ZkMBFYs&ab_channel=Unity

Is this a RLHF session ?

[empty rune]

The example demonstrates Imitation Learning (IL), the model learns to mimic the behavior of an expert. The goal is to replicate the given expert demonstrations as closely as possible.

For RLHF in Unity ML-Agents Toolkit, a reward model is needed to translate human preference into a numerical reward signal

Because you mentioned self-play in the title, please have a look at the blog post about Training intelligent adversaries using self-play with ML-Agents: https://unity.com/blog/engine-platform/training-intelligent-adversaries-using-self-play-with-ml-agents