I am interested in reinforcement learning, and to begin with, I am working on the book "reinforcement learning an introduction 2nd edition" (Richard S.Sutton and Andrew G.Barto), considered as a reference in this field.
In the notebook of this repo you can find my reproduction of figures from chapter 2 of the book related to multi-armed bandits.
-
the book is available here: https://www.andrew.cmu.edu/course/10-703/textbook/BartoSutton.pdf
-
the solution of exercises are available here: https://github.com/LyWangPX/Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions
You need to install some basics Python libraries for running the notebook (numpy, matplotlib ...).
A good way is to work with virtual environment like conda env.
-
install Anaconda or Miniconda on your computer
-
change "prefix" in file: environment.yml
-
create conda env named "rl" by running
conda env create -f environment.yml