CODEWITHSUNDEEP
language-agnosticartificial-intelligencemachine-learningreinforcement-learning
bdd
bdd

Reputation: 3434

Good implementations of reinforcement learning?

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 reinforcement learning in a tetris game?
  2. Are there any good open source projects that accomplish similar things that would be worth checking out?

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

Follow up:

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

Paper / Code

Upvotes: 25

Views: 6682

Answers (4)

Konstantin Tarkus
Konstantin Tarkus

Reputation: 38378

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:

Upvotes: 2

ComputerScientist
ComputerScientist

Reputation: 964

For anyone reading this in 2018, I highly recommend you use OpenAI Baselines if you're interested in solid references of existing RL algorithms. These algorithms are implemented by a group of employees at OpenAI who really know this stuff, and have been extensively fine-tuned and debugged.

To be fair, you don't need these for Tetris, but nowadays I suspect homework questions may involve some more sophisticated environments.

https://github.com/openai/baselines

UPDATE:

in 2019, I also recommend rlpyt:

https://github.com/astooke/rlpyt

Upvotes: 1

Nick Walker
Nick Walker

Reputation: 798

Burlap is a recent Java library that provides implementations of many common reinforcement learning algorithms as well as a few environments and useful tools.

Upvotes: 0

andrewdotn
andrewdotn

Reputation: 34813

Take a look at the 2009 RL-competition. One of the problem domains is a tetris game. There was a tetris problem the year before too. Here’s the 52-page final report from that year’s fifth-place finalist, which goes into a lot of detail about how the agent worked.

Upvotes: 13

Related Questions