Dive deeper into deep reinforcement learning and learn how to improve upon Q learning with policy gradient methods!
Code for this tutorial:
https://github.com/colinskow/move37/tree/master/pg
Highly recommended math primers:
1) If you aren't 100% confident on the subject of logarithms, read up here:
https://www.mathsisfun.com/algebra/logarithms.html
2) Study up on entropy, cross entropy, and KL divergence
https://www.youtube.com/watch?v=ErfnhcEV1O8
3) Study up on the softmax function
https://www.youtube.com/watch?v=mlaLLQofmR8
