"Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward". In this course, you will learn the concepts and the algorithms behind and you will start to apply RL practically.

Build a strong foundation in Reinforcement Learning and its algorithms with this tutorial.

This course is the first of two parts. In this part, we will start with basic concepts and ideas that form the foundation of the RL. Concepts like: Q-Learning and Markov decision processes (MDPs). Then we will learn more recent algorithms (built on deep learning) like Deep Q-Networks. Each module contains a concept illustration together with a real implementation walkthrough (source code is available)

The course consists of 6 lectures (~2 hours of material) described as follows:

• Introduction (1 lecture)

• Markov Decision Process (2 lectures)

• Q-Learning (1 lecture)

• Deep Q-Networks (2 lectures)

Prerequisites

1. Basic Mathematics knowledge

2. Basic Python knowledge

This course started as a youtube series that currently has 16K+ views and a lot of very positive comments. Now it will be available on Udemy for better content management and interaction with students.

I hope you find the course useful and see you in Part 2!