ES == Evolution Strategies
DL == Deep Learning

Every games will be developed on different algorithms:

1. Reward based {ES}
2. Policy gradient {ES, DL}
3. Q-learning {ES, DL}
4. Double Q-learning {ES, DL}
5. Recurrent-Q-learning {DL}
6. Double Recurrent-Q-learning {DL}
7. Dueling Q-learning {DL}
8. Dueling Recurrent-Q-learning {DL}
9. Double Dueling Q-learning {DL}
10. Double Dueling Recurrent-Q-learning {DL}
11. Actor-Critic {DL}
12. Actor-Critic Dueling {DL}
13. Actor-Critic Recurrent {DL}
14. Actor-Critic Dueling Recurrent {DL}

Games that will be developed:

1. Flappy bird
2. level 1 mario
3. pong
4. Catcher
5. Pixelcopter
6. Raycast Maze
7. Snake
8. Water World
9. Dooms

This repository will be update overtime.