Implementation of DQN to play the Flappy Bird game with Oneflow framework .
This work is based on: uvipen/Flappy-bird-deep-Q-learning-pytorch and Ldpe2G/DeepLearningForFun
| Spec | |
|---|---|
| Operating System | Ubuntu 18.04 |
| GPU | Nvidia A100-SXM4-40GB |
| CUDA Version | 11.2 |
| Driver Version | 460.73.01 |
| Oneflow Version | branch: master, commit_id: 90d3277a098f483d0a0e68621b7c8fb2497a6fc2 |
- python3
- pygame
- numpy
- opencv
- Oneflow
bash test_flappy_bird.shbash train_flappy_bird.shIt will take about at least 40000 time steps before the bird can learn to play the game, be patients :).
