This repository contains an PyTorch implementation of "Importance Weighted Actor-Learner Architectures".
For a detailed description of the architecture please read paper.
- Python >=3.7
- PyTorch >=1.2.0
- atari_py >=0.1.7
- cv2 >= 3.4.2
- Experiment's results.
- Try to remove the ParameterServer.
- Distributed Training.
- Other games such as dmlab.