This is DQN implemented as tensorflow 2. It has done under the Open AI gym Carpole-v1 environment. the used methods are the original DQN & multi-step DQN
- Python 3.6.2
- tensorflow 2.1.0
- matplotlib 3.0.2
Training only original DQN.
> python script.py orgDQN
Training original DQN & multi-step in sequence.
> python script.py orgDQN multistep