Good implementations of reinforced learning?

Question

For an ai-class project I need to implement a reinforcement learning algorithm which beats a simple game of tetris. The game is written in Java and we have the source code. I know the basics of reinforcement learning theory but was wondering if anyone in the SO community had hands on experience with this type of thing.

1. What would your recommended readings be for an implementation of reinforced learning in a tetris game?
2. Are there any good open source projects that accomplish similar things that would be worth checking out?

Thanks in advanced

Edit: The more specific the better, but general resources about the subject are welcomed.

Follow up:

Thought it would be nice if I posted a followup.

Here's the solution (code and writeup) I ended up with for any future students :).

Paper / Code

Answer 1

The Heaton Research ebook is quite good at explaining neural network concepts (with code). Chapter 4 is dedicated to machine learning and the various training methods for your networks. There is a downloadable library and sample applications for you to look at.

Answer 2

Here is a good book on the subject:

Machine Learning and Data Mining: Introduction to Principles and Algorithms
by Igor Kononenko, Matjaz Kukar (June, 2007)

Also take a look at these open source projects:

• Maja Machine Learning Framework
• PIQLE
• Elsy
• The Robotics Primer Workbook

Answer 3

Take a look at this year’s RL-competition. One of the problem domains is a tetris game. There was a tetris problem last year too. Here’s the 52-page final report from last year’s fifth-place finalist, which goes into a lot of detail about how the agent worked.

Answer 4

TD-Gammon, gnubackgammon, or any other similar project were massive successes in games.

Sutton & Barto's book "Reinforcement Learning: An Introduction" also has some other Case Studies.

Answer 5

This is not specific to reinforced learning, but Stanford has a great series of lectures on machine learning on Youtube and iTunes.

The link is to the first lecture which takes approximately 30 minutes to dive into the content.

Answer 6

In the follow up posted .. the link for the code - "code" is broken..

can you mail that to me at [email protected]

thanks in advance.

cheers !!

Answer 7

can you please update the link for the code. or please email me at [email protected]

thanking you in anticipation..!! :)