AIsaturdays

DQN-Atari-Tensorflow

Reimplementing "Human-Level Control Through Deep Reinforcement Learning" in Tensorflow

This may be the simplest implementation of DQN to play Atari Games.

Prerequsite

1. Tensorflow (prefer with GPU CUDA supported)
2. opencv2
3. gym -toolkit for developing and comparing reinforcement learning algorithms. ( https://https://github.com/openai/gym )
4. Keras

Setup and Run

git clone https://github.com/pranav014/AIsaturdays.git
cd 
python 

Reference

https://keon.io/deep-q-learning/