Final project for BU EC500 K1/CS591 S2 Deep Learning
- Deep Policy Network
- Dueling Double Deep Q Network
- Dueling Double Deep Q Network with LSTM
- Asynchronous Advantage Actor Critic
- Asynchronous Advantage Actor Critic with GRU
- Python 3.6
- Tensorflow 1.0
- OpenAI Gym
To train the model:
python3 main.py
To train other games or change model parameter, edit the corresponding params.py file.