Deep RL Bootcamp Lecture 4B Policy Gradients Revisited

 https://drive.google.com/file/d/0BxXI_RttTZAhTUpqUFdEZ3BXNFE/view

game of Pong is a MDP.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

终于一睹AK真容了，很有想法，很幽默

 http://karpathy.github.io/