The RL agent can be trained with the following command:
$ python train.py
Information about the command-line arguments can be shown with:
$ python train.py --help
To evaluate the performance of the agent, run:
$ python train.py --eval --load_model "/path/to/trained/model.torch"
The following Python libraries should be available:
- torch (1.1.0)
- pandas (0.24.2)