Usually over the holidays I like to go through ML/RL books for fun as a distraction from med.
So far I've made a start at Dive into Deep Learning and Reinforcement Learning: An Introduction.
Of the RL book, I was able to get up to Part 2 using the approximation methods implemented Vanilla Deep Q Learning for the cartpole problem in JAX!
There's lots more to learn and do under this topic but I'm putting most things on pause as I have to prioritise medical studies.
My cartpole implementation: (notebook here)
