a3C.py 文件源码

def v(self):
        with tf.variable_scope('critic'):
            w_i = tf.random_uniform_initializer(0., 0.1)
            b_i = tf.zeros_initializer()
            with tf.variable_scope('dense1'):
                dense1 = dense(self.state_input, 100, [100], w_i, activation=tf.nn.relu6)
            with tf.variable_scope('dense2'):
                dense2 = dense(dense1, 1, [1], w_i, b_i, activation=None)
            return dense2

    # Note: We need 2 return value here: mu & sigma. So it is not suitable to use lazy_property.