This is a pytorch implementation of "Deep Reinforcement Learning with Double Q-learning". In this lastest version, I use the Atari games. But in the future, I will bring the Flappy Bird back!
- python-3.5.2
- openai-gym
- pytorch-0.4.0
- opencv-python
Install OpenAI Baselines (the openai-baselines update so quickly, please use the older version as blow, will solve in the future.)
# clone the openai baselines
git clone https://github.com/openai/baselines.git
cd baselines
git checkout 366f486
pip install -e .
python train_network.py --cuda (if you have a GPU, you can use this flag)
python demo.py
Please download them from the Google Driver, then put the saved_models under the current folder.
