In this post, readers will see how to implement a decision transformer with OpenAI Gym on a Gradient Notebook to train a hopper-v3 "robot" to hop forward over a horizontal boundary as quickly as possible.
In last weeks tutorial, we learned how reinforcement learning works and applied it to the cart pole problem on Gradient. This week we will look at the cart pole problem in more depth, and show how to use reinforcement learning for complex problem solving!
In this introductory guide, you will learn how the basics of reinforcement learning, and see how it can be applied in practice on a starter project: the cart pole problem.
This post covers how to implement a custom environment in OpenAI Gym. As an example, we implement a custom environment that involves flying a Chopper (or a helicopter) while avoiding obstacles mid-air.
In this post, we describe the anatomy of how most Deep Reinforcement Learning algorithms work. We also cover the motivation to use RL over standard machine learning, On-Policy v/s Off-Policy learning, the Exploration-Exploitation Tradeoff, and many more important RL concepts.
In this article, we'll cover the basic building blocks of Open AI Gym. This includes environments, spaces, wrappers, and vectorized environments.
