/rl-battleship-agent

Primary LanguagePython

Reinforcement Learning Battleship Agent

Usage

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"

Requirements

The following Python libraries should be available:

  • torch (1.1.0)
  • pandas (0.24.2)