es.py 文件源码

def _make_network(self, data_in, out_dim):
        """ Build the network with the same architecture following OpenAI's paper.

        Returns the final *layer* of the network, which corresponds to our
        chosen action.  There is no non-linearity for the last layer because
        different envs have different action ranges.
        """
        with tf.variable_scope("ESAgent", reuse=False):
            out = data_in
            out = layers.fully_connected(out, num_outputs=64,
                    weights_initializer = layers.xavier_initializer(uniform=True),
                    #weights_initializer = utils.normc_initializer(0.5),
                    activation_fn = tf.nn.tanh)
            out = layers.fully_connected(out, num_outputs=64,
                    weights_initializer = layers.xavier_initializer(uniform=True),
                    #weights_initializer = utils.normc_initializer(0.5),
                    activation_fn = tf.nn.tanh)
            out = layers.fully_connected(out, num_outputs=out_dim,
                    weights_initializer = layers.xavier_initializer(uniform=True),
                    #weights_initializer = utils.normc_initializer(0.5),
                    activation_fn = None)
            return out