[UPDATE] Potentially incorrect terminology in unit 2 midway recap
lutzvdb opened this issue · 3 comments
What do you want to improve?
In Unit 2 (Midway Recap) (units/en/unit2/mid-way-recap.mdx) the following is stated:
There are two types of methods to learn a policy for a value function:
Now, I'm only just learning all about reinforcement learning, but before, it was clearly stated that for the value-based methods the function was pre-defined and fixed. I think it could be more appropriate to say something along the lines of:
There are two types of methods to update the value function
Please let me know if I'm misunderstanding; however, to me, this seems misleading and makes understanding harder.
Hey there 👋 ,
Indeed you're right!
Do you want to open a PR with your phrase so that you can be added as contributor? 🤗
Merged and thanks again 🤗