gaussian.py 文件源码

def _make_actiondist_ops(self, obs_B_Df):
        with tf.variable_scope('flat'):
            flat = nn.FlattenLayer(obs_B_Df)
        with tf.variable_scope('hidden'):
            net = nn.FeedforwardNet(flat.output, flat.output_shape, self.hidden_spec)
        with tf.variable_scope('out'):
            mean_layer = nn.AffineLayer(net.output, net.output_shape, self.action_space.shape,
                                        Winitializer=tf.zeros_initializer, binitializer=None)

        means_B_Da = mean_layer.output

        # logstdev params
        logstdevs_1_Da = tf.get_variable('logstdevs_1_Da', shape=(1, self.action_space.shape[0]),
                                         initializer=tf.constant_initializer(self.init_logstdev))
        stdevs_1_Da = self.min_stdev + tf.exp(
            logstdevs_1_Da)  # Required for stability of kl computations
        stdevs_B_Da = tf.ones_like(means_B_Da) * stdevs_1_Da

        actiondist_B_Pa = tf.concat(1, [means_B_Da, stdevs_B_Da])
        return actiondist_B_Pa