资 源 简 介
This is a set of Java classes that demonstrate reinforcement learning algorithms. They were developed in 2004 while studying Reinforcement Learning for application with Intelligent Agents. For more information on this see my thesis "Reasoning and Learning for Intelligent Agents".
These example classes simply follow the exercises as described in the book "Reinforcement Learning: An Introduction" by Sutton and Barto. An online version of this book can be found here:
http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html