Take the 2-minute tour ×
Computational Science Stack Exchange is a question and answer site for scientists using computers to solve scientific problems. It's 100% free, no registration required.

[I hope this is the correct place to post - if not, please feel free to migrate the question to another site].

I would like to build a computer program that will play games effectively, and I want to use reinforcement learning techniques, namely, let two copies of the program play against each other, and use http://en.wikipedia.org/wiki/Temporal-difference_learning for learning an optimal strategy.

Before I start coding - is there an existing framework for such tasks? Preferrably in Java, but not necessarily.

I found some Java frameworks for reinforcement learning, but they are not geared towards games.

share|improve this question
This might be better on stats.stackexchange.com, but I don't know for sure. –  tpg2114 Nov 2 '12 at 13:16
Thanks, you are probably right, I posted my question there and got some answers. –  Erel Segal Halevi Nov 5 '12 at 15:29

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.