gistfile1.txt

def policy_network(state, max_layers):
    with tf.name_scope("policy_network"):
        nas_cell = tf.contrib.rnn.NASCell(4*max_layers)
        outputs, state = tf.nn.dynamic_rnn(
            nas_cell,
            tf.expand_dims(state, -1),
            dtype=tf.float32
        )
        bias = tf.Variable([0.05]*4*max_layers)
        outputs = tf.nn.bias_add(outputs, bias)
                return outputs[:, -1:, :]