Video Description
This course provides an introduction to the field of reinforcement learning and the use of OpenAI Gym software. It details the terminology and core concepts of reinforcement learning, illustrates how OpenAI Gym software incorporates those core concepts, and shows you how to code solutions for reinforcement learning problems present in simple mazes and complex Atari games. Requirements include basic Python programming experience, basic math knowledge, familiarity with the Linux and Bash terminal, and an understanding of how to use Jupyter notebooks.
- Master the basic terminology, concepts, and uses of reinforcement learning
- Understand how to install and manage reinforcement learning software
- Learn about OpenAI Gym's API and how to use it to test reinforcement learning algorithms
- Discover how to determine if a problem is best solved with reinforcement learning
- Explore the code used to solve reinforcement learning problems in computer games
Justin Francis runs Allisee Solutions, a machine learning training company based on Canada's West Coast. Justin is a frequent contributor to O'Reilly Media as the author of numerous articles on the topics of TensorFlow, reinforcement learning, and OpenAI Gym. A self-taught programmer, Justin holds certifications in machine learning, data science ethics, and Java programming.
Table of Contents
-
Introduction
- Welcome To The Course 00:01:56
- About The Author 00:00:39
-
Software Installation
- Machine Learning Software 00:02:22
- Anaconda Virtual Environments 00:02:25
- OpenAI Gym Installation 00:01:36
-
Basics Of Reinforcement Learning And OpenAI
- What Is Reinforcement Learning? 00:02:27
- Reinforcement Learning Terminology 00:03:22
- OpenAI Gym Basics 00:04:42
- OpenAI Gym Environments 00:00:40
-
Key Reinforcement Learning Concepts
- Markov Decision Processes 00:01:49
- Solving Markov Decision Processes 00:03:15
- How To Determine A Reinforcement Learning Problem 00:02:16
-
Simple Reinforcement Learning Problems In OpenAI Gym
- Solving Taxi Environment 00:03:54
- Solving Frozen Lake Environment - Part 1 00:02:46
- Reward Discounting 00:02:09
- Solving Frozen Lake Environment - Part 2 00:02:52
- Deep Reinforcement Learning With OpenAI Gym And TensorFlow
-
Conclusion
- Wrap Up And Thank You 00:01:27