LyWangPX / Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions

Solutions of Reinforcement Learning, An Introduction

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ex 11.2 typo

tomasruizt opened this issue · comments

Hi :) you may want to complete in the first line the q function with the missing action:
q(S, w) to q(S, A, w).

The next is just nitpicking, but if you want to harmonize the notation with the book, then the approximation of V is written in lowercase and with hat instead of bar.

Cheers :)

That's a valid point. Thanks.
I got some other similar advices and I may update them altogether in the near future.