Hacker News Reader

The code is online if you want to play with it. https://sites.google.com/a/deepmind.com/dqn/

If you're interested, one of the main authors (David Silver) teaches a very good and intuitive introductory class on reinforcement learning at UCL: http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html

View on HN

Interesting that they're using Torch7. The code is pretty concise and readable, very cool stuff.

They wrote Torch7...

I'm sure a number of people who have contributed to Torch are working at DeepMind. However, Torch has been around for much longer than DeepMind (about 12 years at this point). Two of the major contributors to Torch, Ronan Collobert and Clement Farabet, were never DeepMind employees.

To be fair, another major contributor to Torch is a co-author of this paper (Kavukcuoglu).

Reply on news.ycombinator.com