A3C.py 文件源码

def _build_net(self):
        with tf.variable_scope("conv"):
            out = layers.convolution2d(self.s, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("actor"):
            a_prob = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            a_prob = layers.fully_connected(a_prob, num_outputs=N_A, activation_fn=tf.nn.softmax)

        with tf.variable_scope("critic"):
            v = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            v = layers.fully_connected(v, num_outputs=1, activation_fn=tf.nn.softmax)

        return a_prob, v