a3C.py 文件源码

def a_prob(self):
        with tf.variable_scope('actor'):
            w_i = tf.random_uniform_initializer(0., 0.1)
            b_i = tf.zeros_initializer()
            with tf.variable_scope('dense1'):
                dense1 = dense(self.state_input, 200, None, w_i, b_i, activation=tf.nn.relu6)
            with tf.variable_scope('dense2'):
                dense2 = dense(dense1, self.action_dim, None, w_i, b_i, activation=tf.nn.softmax)
            return dense2