Deep-RL

Udacity Deep RL ND

NOTE: At this point, the "latex.codecogs.com" equation renderer that I use for all the math equations in the notes is not working. So, from this point on (proximal policy lesson, credit assignment section), I will write the latex codes directly. Probably, most the equations I wrote using this website is not rendering throughout the notes, so they need to be fixed at some point as well.

Other Resources:

• Grokking Deep Reinforcement Learning.
• Shangtong Zhang GitHub repos (coded RL algorithms):
  • DeepRL
  • Reinforcement Learning - An Introduction