Reinforcement Learning Algorithms with Python

DNNs

The DNN architecture is as follows (the components are built in sequential order):

1. A convolution of 16 filters of dimension 8 x 8 with 4 strides and rectifier nonlinearity.
2. A convolution of 32 filters of dimension 4 x 4 with 2 strides and rectifier nonlinearity.
3. A convolution of 32 filters of dimension 3 x 3 with 1 strides and rectifier nonlinearity.
4. A dense layer of 128 units and ReLU activation.
5. A dense layer with a number of units equal to the actions that are allowed in the environment and a linear activation.

In cnn, we define the first three convolutional layers, while in fnn, we define the last two dense layers:

def cnn(x):    x = tf.layers.conv2d(x, filters=16, kernel_size=8, strides=4, padding='valid', activation='relu')  x ...