danieloaAAU / Deep-Reinforcement-Learning-DQN

Deep Reinforcement Learning with DQN, Double DQN, Dueling DQN, Noisy Net (Noisy DQN), and DQN with Prioritized Experience Replay

Deep-Reinforcement-Learning-DQN

Deep Reinforcement Learning containing

1. DQN
2. Double DQN
3. Dueling DQN
4. Noisy Net (Noisy DQN)
5. DQN with Prioritized Experience Replay
6. Noisy Double DQN with Prioritized Experience Replay
7. Noisy Dueling Double DQN with Prioritized Experience Replay

Dependencies

1. python 3.6
2. tensorflow 1.12.0
3. cuda 9.0
4. cuDNN 7.1.4

Results

the results are the mean of the scores in each 200 episodes of cartpole-v1.

tutorial

link to the tutorial: link