Implementation DQN as specified in Human Level Control Through Deep Reinforcement Learning. Knowledge of the paper is expected.
- Create a virtual environment (venv, pipenv, conda, ...) with Python 3 (Python 3.7.4 recommended) and pip
- Execute
pip install -r requirements.txt
- Navigate into the root directory (containing setup.py) and install package by
pip install -e .
- Make sure you have CUDA installed (essentially any version compatible with pytorch, see below)
- Install pytorch to match your CUDA version (project was built for pytorch 1.2, so keep this in mind when deciding what pytorch-CUDA combination to install)
Work in progress. See Github project of this repository for details.