Reinforcement Learning (RL) is the kind of machine learning closest to how humans and animals learn. It offers us a path towards building general AI systems that can tackle the most complex problems we can think of. In this reinforcement learning course, I will teach you how.
Welcome to the Hands-on reinforcement learning course ❤️
Let’s walk this beautiful path from the fundamentals to cutting edge deep reinforcement learning, together!
👉🏽From zero to HERO 🦸🏻🦸🏼🦸🏽🦸🏾🦸🏿🦸♂️🦸♀️
👉🏽Step by step
👉🏽Clean Python code
👉🏽Intuitions, tips and tricks explained.
Code
All the reinforcement learning course code is in this Github repo. Don’t forget to give it a ⭐!
Lectures
![reinforcement learning course](https://datamachines.xyz/wp-content/uploads/2021/11/PHOTO-2021-11-05-13-54-11-1024x768.jpg)
1. Introduction to Reinforcement Learning
This first part covers the bare minimum concept and theory you need to embark on this journey, with practical examples and the first code snippet!
![reinforcement learning course](https://datamachines.xyz/wp-content/uploads/2021/11/pexels-helena-jankovičová-kováčová-5870314-1024x681.jpg)
Q learning is a classical RL algorithm published in the 90s. In this first lesson, we use tabular Q-learning to train a smart taxi driver. Ready to drive?
![sarsa](https://datamachines.xyz/wp-content/uploads/2021/12/Belgrade-1024x768.jpg)
The Mountain Car problem is an environment where gravity exists (what a surprise) and the goal is to help a poor car win the battle against it.
SARSA is a classical online algorithm that solve this problem like a charm.
![parametric q learning](https://datamachines.xyz/wp-content/uploads/2022/01/pexels-yogendra-singh-1701202-1024x682.jpg)
4. Parametric Q learning to keep the balance (1/3)
Parametric Q learning combines the strengths of classical Q-learning with modern optimization techniques from Supervised Machine Learning.
![deep q learning](https://datamachines.xyz/wp-content/uploads/2022/02/turtle-1024x682.jpeg)
5. Deep Q learning to keep the balance (2/3)
Let’s replace the linear model from the previous lesson with a deep neural network. And kick-ass solve the Cart Pole environment.
![](https://datamachines.xyz/wp-content/uploads/2022/03/boxed-water-is-better-5Lw1U5BIumE-unsplash-1024x684.jpg)
Hyperparameters in Deep RL are critical to training successful agents. In today’s lesson, we will learn how to find the ones that make you a happy Deep RL developer.
![](https://datamachines.xyz/wp-content/uploads/2022/03/kai_pau_2-1024x768.jpeg)
Deep Learning: Faster, Better, And Free In 3 Easy Steps
Tired of training deep learning models on your laptop, at the speed of… a turtle? 🐢 Not enthusiastic about buying an expensive GPU or optimizing cloud services bills? 💸 Wish there was a better way to do it?
Luckily for you, the answer to the last question is yes.
![](https://datamachines.xyz/wp-content/uploads/2022/05/jagoda_and_kai-1024x768.jpg)
7. Policy Gradients to get to the Moon
Policy gradients are a family of powerful reinforcement learning algorithms that can solve complex control tasks. In today’s lesson, we will implement vanilla policy gradients from scratch and land on the Moon 🌗.
Let’s connect
Wanna become a better data scientist and land a top job? I am here to help you. Subscribe to my newsletter to be notified about all the content I share👇🏽👇🏽👇🏽