Deep-Q-Learning

An implementation of Q algorithm and its deep variant for Reinforcement Learning purposes.

This was a part of Charles Isbell, Michael Littman and Pushkar Kolhe Udacity https://www.udacity.com/course/machine-learning-reinforcement-learning--ud820 Reinforcement Learning course.

Other resources

• Richard S. Sutton and Andrew G. Barto Book

• http://mnemstudio.org/path-finding-q-learning-tutorial.htm

• https://en.wikipedia.org/wiki/Q-learning

• http://arxiv.org/pdf/1312.5602v1.pdf