- contains implemention of dueling network with double q network Hado van Hasselt, Arthur Guez, David Silver, "Deep Reinforcement Learning with Double Q-learning"
- Easy to implement deeprl models
- trainer class
- Actor Critic DDPG
- Q value
- Double Q value
- Simple Policy gradient
1. Tensorflow
2. tqdm
3. gym
4. scipy or opencv (python)
5. Easydict