- Datasets
- Literature
- Function Approximation
- Sutton & Barto
- Quick QLearning Tutorial - https://studywolf.wordpress.com/2012/11/25/reinforcement-learning-q-learning-and-exploration/
- Check this for the implementation and data structures
- Read relevant chapter in Sutton & Barto: https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node65.html
- Deep QLearning with Neural Nets for Function Approx - https://www.nervanasys.com/demystifying-deep-reinforcement-learning/
- Don't fret, this is very simple and has well asbtracted ideas. Mainly focuses on function approximation.
- Read all the sections, they've been explained as black boxes.
- Experience Replay: Online training in minibatches.