- Linear Algebra and Calculus refresher from Stanford Machine Learning course
- Linear Algebra Review and Reference from Stanford
- Computational Linear Algebra for Coders from fast.ai.
- Derivatives, Backpropagation, and Vectorization from Stanford.
- Vector, Matrix, and Tensor Derivatives from Stanford.
- The Matrix Calculus You Need For Deep Learning from fast.ai.
- Probabilities and Statistics refresher from Stanford Machine Learning course
- Review of Probability Theory from Stanford.
- Convolutional Neural Networks for Visual Recognition from Stanford. Thorough and easy to follow course.
- fast.ai course by Jeremy Howard et al. Geared towards coders, top-down methodology.
- deeplearning.ai course by Andrew Ng. Some say it's a bit basic, but he explains extremely well.
- Neural Networks and Deep Learning by Michael Nielsen. More of tutorial style, some very good explanations, i.e. the chapter about universal approximators.
- Deep Learning with Python by Francois Chollet, author of Keras. Excellent down-to-earth practical introduction, with many advanced examples.
- Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville. The definitive reference if you already know a bit.
- UCL Course on RL by David Silver. Very good lectures about basics, but not much deep RL.
- Deep Reinforcement Learning course by Sergey Levine. Covers a lot of material, especially from control theory perspective. Might be hard to follow.
- Reinforcement Learning course from Stanford. Easiest to follow, but not as thorough as previous two.
- Spinning Up in Deep RL from OpenAI. See also this workshop video.
- Reinforcement Learning: An Introduction by Richard Sutton and Andrew Barto. The definitive introduction and reference.
- Learning to Act chapter in Artificial Intelligence: Foundations of Computational Agents book by David Poole and Alan Mackworth. Some good examples of tabular Q-learning.
- Reinforcement learning in Scholarpedia. Good review of challenges in RL.
- PhD thesis by John Schulman - technically not a book, but provides a good overview of RL by one of the most prominent researchers in the field.