Warwick AI
Overview

Resources

November 19, 2026
3 min read
index

Stuff we’d actually recommend if you’re getting into AI. New to all this? Start at the top.

How long it takes

πŸ•’ an afternoon or less Β· πŸ•’πŸ•’ a few days to a week Β· πŸ•’πŸ•’πŸ•’ a few weeks or more

How technical it is

πŸ”₯ beginner friendly Β· πŸ”₯πŸ”₯ some maths/coding needed Β· πŸ”₯πŸ”₯πŸ”₯ heavy going

⭐ = my favourites/ highly recommended


Start here

3Blue1Brown – Neural Networks πŸ•’ πŸ”₯ ⭐

Really nice visual explanation of how neural nets learn. You can watch it on the bus. Trust bro you’re going to like it

Andrew Ng – Machine Learning Specialization πŸ•’πŸ•’πŸ•’ πŸ”₯

It’s a classic and pretty much everyone’s done it. Good grounding in the basics.

Karpathy – Neural Networks: Zero to Hero πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯ ⭐

Starts with backprop by hand and ends with you building a GPT from scratch. Karpathy is one of the leading AI researchers who worked at Tesla, OpenAI, Anthropic. V good course


Deep learning

Dive into Deep Learning πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯

Textbook with code you can run for every section. Free online, or you can buy it in print.

Stanford CS231n πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯πŸ”₯

Stanford’s computer vision course. The lecture notes on CNNs and backprop are some of the best out there.

fast.ai – Practical Deep Learning for Coders πŸ•’πŸ•’πŸ•’ πŸ”₯

You train real models from lesson one and pick up the theory along the way. Good if you learn by doing.

The Illustrated Transformer πŸ•’ πŸ”₯πŸ”₯ ⭐

Jay Alammar’s diagrams of how transformers work. Read this before you try to understand any LLM paper.


Reinforcement learning

Learning it

Spinning Up in Deep RL πŸ•’πŸ•’ πŸ”₯πŸ”₯ ⭐

OpenAI’s written intro to RL and the main policy gradient algorithms, with reference code. Best place to start.

Deriving the simplest policy gradient πŸ•’ πŸ”₯πŸ”₯πŸ”₯

The section of Spinning Up where policy gradients finally click.

Karpathy – Pong from Pixels πŸ•’ πŸ”₯πŸ”₯

The 🐐 Karpathy again. Trains a Pong agent in about 130 lines of Python.

Hugging Face Deep RL Course πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯

Free and hands on, from Q-learning up to PPO, with notebooks.

David Silver’s RL lectures πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯πŸ”₯

The UCL course from the guy who led AlphaGo. Proper theory.

Sutton & Barto πŸ•’πŸ•’πŸ•’ πŸ”₯πŸ”₯πŸ”₯

The og bible. Free PDF. More of a reference than something you read cover to cover.

Going further

The 37 Implementation Details of PPO πŸ•’πŸ•’ πŸ”₯πŸ”₯πŸ”₯ ⭐

The PPO bible. All the stuff the paper leaves out that you need to actually get it working.

Entity-Based RL πŸ•’ πŸ”₯πŸ”₯πŸ”₯

Clemens Winter on entity encoding, which is a cornerstone once your observations get complicated.

Libraries

Gymnasium πŸ”₯

The standard environment API. Pretty much everything below plugs into it.

Stable-Baselines3 πŸ”₯

Best beginner library. Get an agent training in a few lines.

CleanRL πŸ”₯πŸ”₯

Best library for learning. Each algorithm is one readable file.

PufferLib πŸ”₯πŸ”₯πŸ”₯

Best library for frontier work. Very fast.


Tooling

10 minutes to pandas πŸ•’ πŸ”₯

Fundamental for datascience/ ML work.

NumPy for absolute beginners πŸ•’ πŸ”₯

Arrays and broadcasting. Everything else is built on this.

PyTorch tutorials πŸ•’πŸ•’ πŸ”₯πŸ”₯

Start with β€œLearn the Basics”.

Weights & Biases πŸ”₯

Logs your training runs so you can compare them instead of scrolling back through your terminal.

uv πŸ”₯

Fast Python package and environment manager. Will save you a lot of dependency pain.