Learning Breakout More Quickly

philoxenic

Rate me:

5.00/5 (3 votes)

30 Jun 2020CPOL3 min read

7.5K

In this article, we will see how you can use a different learning algorithm (plus more cores and a GPU) to train much faster on the mountain car environment.

Here we look at: Inspecting the environment, an overview of Ray’s Architecture, and using Impala for learning Breakout more quickly.

Views

Daily Counts

This article is part of the series 'Deep Reinforcement Learning and Game Optimization ◁ Prev View All Next ▷

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Written By

philoxenic

Web Developer

United Kingdom

This member has not yet provided a Biography. Assume it's interesting and varied, and probably something to do with programming.

Comments and Discussions

Cartpole: The “Hello World” of Reinforcement Learning

Cartpole: Tweaking the Options

Introduction to OpenAI Gym: Atari Breakout

Learning Breakout More Quickly

Learning Breakout From RAM – Part 1

Learning Breakout From RAM – Part 2

Learning Breakout: Advanced Topics

Go to top