Our agent is currently training: we'll launch our first video on Tuesday 27th
We're using the architecture A3C, : Asynchronous Advantage Actor Critic. We're currently writing an article about it. It will be available on Tuesday.
If you want to contribute to the project, your help is very welcome. This AI is an open source project.
We currently working on improving our Deep Neural Network architecture, adding new games such as Super Mario Bros etc... If you're motivated come join us!