I appreciate the effort and the time that went into writing this, but this blog is of really low quality and I'll try to argument why I mean that concisely:

1. You're mixing up control theory/RL notation. Nobody cares that there are multiple notations out there, we're all aware of that. Please stick to a single notation, otherwise a chunk of the cognitive bandwidth goes into parsing syntax instead of focusing on the semantics.

2. The structure of the blog is weird - you mention deep learning at the end of the blog but you've been referencing it along the way - that's just 1 example there are many more. You need to develop the story and gradually introduce the concepts.

3. It's not clear whether this blog is meant as an introduction or a mix of everything that came to your mind. Lots of maths thrown around without any explanation.

4. Lastly the English grammar is very bad. I'm aware that English is not your native language, but please install Grammarly or some similar grammar-checking app. Again, bad grammar makes it much harder to focus on semantics.

This is meant as a feedback and not me throwing a hate at your blog. But I "wasted" (not a complete waste of time I don't want to be rude) 20 minutes of my time and I'm afraid many others will so I felt like spending additional 5 mins to write this down.

What brought me here in the first place was the fact that this blog has 2.6 K likes but that's unfortunately misleading and it's a shame that Medium doesn't allow for negative signals like dislikes.