不錯的練習
http://www.wildml.com/2016/10/learning-reinforcement-learning/
解釋
https://mpatacchiola.github.io/blog/2016/12/09/dissecting-reinforcement-learning.html
課本
http://ufal.mff.cuni.cz/~straka/courses/npfl114/2016/sutton-bookdraft2016sep.pdf
Q vs SARSA https://studywolf.wordpress.com/2013/07/01/reinforcement-learning-sarsa-vs-q-learning/