Awesome Open Source
Awesome Open Source


Introduction to Making a Simple Game AI with Deep Reinforcement Learning


Minimal and Simple Deep Q Learning Implemenation in Keras and Gym. Under 100 lines of code!

The explanation for the code is covered in the blog article

I made minor tweaks to this repository such as load and save functions for convenience.

I also made the memory a deque instead of just a list. This is in order to limit the maximum number of elements in the memory.

The training might be unstable for This problem is mitigated in I'll cover ddqn in the next article.

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (53,199
deep-learning (3,906
reinforcement-learning (551
deep-reinforcement-learning (200
dqn (74
deep-q-network (24