Keras

Deep Reinforcement learning

A deep reinforcement learning walkthrough: building a DQNetwork with TensorFlow 2 and running Q-learning against OpenAI Gym's MountainCar environment.

Machine Learning

Tensorflow2 -- MNIST

TensorFlow 2.x 實作 MNIST 手寫數字辨識：比較繼承 tf.keras.Model 與 Sequential API 兩種建模方式，以及 GradientTape 自訂訓練迴圈的完整程式碼。