My implementation of the PDD-DQN algorithm. The PDD-DQN is an improvement of the classic DQN. It includes the following improvements:
- Double Q-learning (https://arxiv.org/abs/1509.06461)
- Dueling Network Architectures (https://arxiv.org/abs/1511.06581)
- Prioritized Experience Replay (https://arxiv.org/abs/1511.05952)