/hands-on-rl

Primary LanguageJupyter Notebook

The Hands-on Reinforcement Learning course 🚀

From zero to HERO 🦸🏻‍🦸🏽

Out of intense complexities, intense simplicities emerge

--Winston Churchill

Welcome ❤️

Welcome to my step by step hands-on-course that will take you from basic reinforcement learning to cutting-edge deep RL.

We will start with a short intro of what RL is, what is it used for, and how does the landscape of current RL algorithms look like.

Then, in each following chapter we will solve a different problem, with increasing difficulty:

  • 🏆 easy
  • 🏆🏆 medium
  • 🏆🏆🏆 hard

Ultimately, the most complex RL problems involve a mixture of reinforcement learning algorithms, optimizations and Deep Learning techniques.

You do not need to know deep learning (DL) to follow along this course.

I will give you enough context to get you familiar with DL philosophy and understand how it becomes a crucial ingredient in modern reinforcement learning.

Contents

  1. Introduction to Reinforcement Learning
  2. Q-learning to drive a taxi 🏆
  3. SARSA to beat gravity 🏆

00. Intro to reinforcement learning

👉 Read in datamachines 👉 Read in Towards Data Science

  • What is a Reinforcement Learning problem? 🤔
  • Policies 👮🏽 and value functions.
  • How to generate the training data? 📊
  • Python boilerplate code.🐍
  • Recap ✨
  • Homework 📚
  • What’s next? ❤️

01. Q-Learning to drive a taxi 🏆

👉 Read in datamachines 👉 Read in Towards Data Science

  • The taxi driving problem 🚕
  • Environment, actions, states, rewards
  • Random agent baseline 🤖🍷
  • Q-learning agent 🤖🧠
  • Hyper-parameter tuning 🎛️
  • Recap ✨
  • Homework 📚
  • What's next? ❤️

02. SARSA to beat gravity 🏆

👉 Read in datamachines 👉 Read in Towards Data Science

  • The Mountain car problem 🚃
  • Environment, actions, states, rewards
  • Random agent baseline 🚃🍷
  • SARSA agent 🚃🧠
  • Take a pause and breath ⏸🧘
  • Recap ✨
  • Homework 📚
  • What’s next? ❤️