The Hands-on Reinforcement Learning course ๐
From zero to HERO ๐ฆธ๐ปโ๐ฆธ๐ฝ
Out of intense complexities, intense simplicities emerge
--Winston Churchill
Welcome โค๏ธ
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:
- ๐ easy
- ๐๐ medium
- ๐๐๐ 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
- Introduction to Reinforcement Learning
- Q-learning to drive a taxi ๐
- SARSA to beat gravity ๐
00. Intro to reinforcement learning
๐ Read in datamachines ๐ Read in Towards Data Science
- What is a Reinforcement Learning problem? ๐ค
- Policies ๐ฎ๐ฝ and value functions.
- How to generate the training data? ๐
- Python boilerplate code.๐
- Recap โจ
- Homework ๐
- Whatโs next? โค๏ธ
01. Q-Learning to drive a taxi ๐
๐ Read in datamachines ๐ Read in Towards Data Science
- The taxi driving problem ๐
- Environment, actions, states, rewards
- Random agent baseline ๐ค๐ท
- Q-learning agent ๐ค๐ง
- Hyper-parameter tuning ๐๏ธ
- Recap โจ
- Homework ๐
- What's next? โค๏ธ
02. SARSA to beat gravity ๐
๐ Read in datamachines ๐ Read in Towards Data Science
- The Mountain car problem ๐
- Environment, actions, states, rewards
- Random agent baseline ๐๐ท
- SARSA agent ๐๐ง
- Take a pause and breath โธ๐ง
- Recap โจ
- Homework ๐
- Whatโs next? โค๏ธ