This sample is published as part of the corresponding blog article at https://www.toptal.com/deep-learning/pytorch-reinforcement-learning-tutorial
Visit https://www.toptal.com/blog and subscribe to our newsletter to read great posts!
- Python 3.6.5
- Run
pip3 install -r requirements.txt
to install dependencies.
- Run
python dqn.py test
to run pretrained neural network model. - Run
python dqn.py train
to train the model from the beginning. You can also increase FPS in game/flappy_bird.py script for faster training.
References:
- https://github.com/sourabhv/FlapPyBird
- https://github.com/yenchenlin/DeepLearningFlappyBird -> modified FlapPyBird game engine adjusted for reinforcement learning is used from this TensorFlow project
- https://ai.intel.com/demystifying-deep-reinforcement-learning/
- https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
- https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf
- http://cs229.stanford.edu/proj2015/362_report.pdf
- https://en.wikipedia.org/wiki/Convolutional_neural_network
- https://en.wikipedia.org/wiki/Reinforcement_learning
- https://en.wikipedia.org/wiki/Markov_decision_process
- http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html
- https://en.wikipedia.org/wiki/Flappy_Bird
- https://pytorch.org/