qlearner.py 文件源码

def inject_summaries(self, idx):
        if len(self._stats_mean_qvalues) > 0:
            self.visualize(idx, "%s/episode mean q" % self.name,
                           np.asscalar(np.mean(self._stats_mean_qvalues)))
            self.visualize(idx, "%s/episode mean stddev.q" % self.name,
                           np.asscalar(np.mean(self._stats_stddev_qvalues)))

        if len(self._stats_loss) > 0:
            self.visualize(idx, "%s/episode mean loss" % self.name,
                           np.asscalar(np.mean(self._stats_loss)))

        if len(self._stats_rewards) > 0:
            self.visualize(idx, "%s/episode mean reward" % self.name,
                           np.asscalar(np.mean(self._stats_rewards)))

            # Reset
            self._stats_mean_qvalues = []
            self._stats_stddev_qvalues = []
            self._stats_loss = []
            self._stats_rewards = []