比如下面这些代码，来自如下链接代码中的182行：https://github.com/PaddlePaddle/PARL/blob/develop/parl/algorithms/fluid/ppo.py

        pg_ratio = layers.exp(logprob - old_logprob)
        clipped_pg_ratio = layers.clip(pg_ratio, 1 - self.epsilon,
                                       1 + self.epsilon)
        surrogate_loss = layers.elementwise_min(
            advantages * pg_ratio, advantages * clipped_pg_ratio)
        loss = 0 - layers.reduce_mean(surrogate_loss)