In this project, we propose the new rainforcement learning model called "Sequential-Multi-Agent".
This project require following environments.
| Environment | Version |
|---|---|
| Python | 3.6.x or later |
| Pytorch | 1.2.0 |
| Torchvision | 0.4.0 |
| numpy | 1.16.x |
| TensorBaordX | 1.9 |
And also this project require GPU environment.
This project use following Benchmark game.
- Open AI Gym - Atari Pong NoFrameSkip-v4
Rf) Open AI Gym - Pong-v0
Use src/app.py for training and tesing the model.
Once executed, learning is executed with the default hyperparameter configrations.
This software is released under the Apache License 2.0, see LICENSE.