A series of blog posts and associated python code samples that closely mirror the infamous Lecture Series by David Silver.
Most if not all images are stolen from his lecture slides, and the blog posts linked below all follow the lectures in structure.
For the best experience clone the repo and open the notebooks locally. Github doesn't support images in jupyter markdown cells.
Lecture 1: Not another RL Tutorial!
An overview of the RL problem. Lays some of the groundwork for more rigorous posts to come.
Lecture 2: Chains, Rewards, and Decision Processes, Oh My!
Goes over Markov Chains, Reward Processes, and Decision Processes with basic implementations in python notebooks.