TensorFlow implementation of Deep Reinforcement Learning papers based on deep Q-learning (DQN).
[1] Human-Level Control through Deep Reinforcement Learning
[2] Deep Reinforcement Learning with Double Q-learning
[3] Prioritized Experience Replay
[4] Dueling Network Architectures for Deep Reinforcement Learning
- update to tensorflow 1.+
- add experimental results
- Python 2.7x
- TensorFlow
- Openai gym
- numpy
- tqdm
Mahmoud I.Zidan @ZidanMusk