In the last few weeks I’ve been compiling a set of notes and exercise solutions for Sutton and Barto’s Reinforcement Learning: An Introduction. Admittedly, these were produced for my own benefit, but if you’d like to look at my notes, my (probably incorrect) answers to the exercises, or the code accommodating those answers, I’ll link directly to them below:

Thanks to Bryn Hayder for inspiring this idea, and for providing his exercise solutions which helped me throughout.