/Replicating-DeepMind

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind

Primary LanguageC++GNU General Public License v3.0GPL-3.0

Replicating-DeepMind

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind. All the information is in our Wiki.

Progress: 'smart' agent is playing, chooses an action based on a randomly initalised neural network.

Alert! The system is not fully ready! At the moment we are re-implementing the neural network using cuda-convnet2. Hopefully everything will be functional by December.