5c81c1c3138d296b8ac5f836e118cfb849b7bf5d,softqlearning/algos/softqlearning.py,SoftQLearning,_evaluate,#SoftQLearning#Any#,464

Before Change

            ("Epoch", epoch),
            ("Alpha", self._alpha),
            ("DiscountedReturnAvg", average_discounted_return),
            ("TotalReturnAvg", np.mean(total_returns)),
            ("TotalReturnMin", np.min(total_returns)),
            ("TotalReturnMax", np.max(total_returns)),
            ("TotalReturnStd", np.std(total_returns))
        ])

        for key, value in statistics.items():

After Change

        ]

        episode_lengths = [
            len(p["rewards"]) for p in paths
        ]

        statistics = OrderedDict([

Instances