In this Deep Q-Learning, aka Deep Q-Network (DQN), tutorial series, we'll code up the algorithm with PyTorch and train FlappyBird. In this video, we'll implement the Experience Replay module that will be used for collecting the bird's "experiences", so that we could send the experiences into the network. We'll also configure the hyperparameters as a yaml file.
Github code: github.com/johnnycode8/dqn_py...
Support me here: www.buymeacoffee.com/johnnycode