callbacks.py 文件源码

def on_step_begin(self, step, logs):
        if self.step % self.interval == 0:
            if len(self.episode_rewards) > 0:
                metrics = np.array(self.metrics)
                assert metrics.shape == (self.interval, len(self.metrics_names))
                formatted_metrics = ''
                if not np.isnan(metrics).all():  # not all values are means
                    means = np.nanmean(self.metrics, axis=0)
                    assert means.shape == (len(self.metrics_names),)
                    for name, mean in zip(self.metrics_names, means):
                        formatted_metrics += ' - {}: {:.3f}'.format(name, mean)

                formatted_infos = ''
                if len(self.infos) > 0:
                    infos = np.array(self.infos)
                    if not np.isnan(infos).all():  # not all values are means
                        means = np.nanmean(self.infos, axis=0)
                        assert means.shape == (len(self.info_names),)
                        for name, mean in zip(self.info_names, means):
                            formatted_infos += ' - {}: {:.3f}'.format(name, mean)
                print('{} episodes - episode_reward: {:.3f} [{:.3f}, {:.3f}]{}{}'.format(len(self.episode_rewards), np.mean(self.episode_rewards), np.min(self.episode_rewards), np.max(self.episode_rewards), formatted_metrics, formatted_infos))
                print('')
            self.reset()
            print('Interval {} ({} steps performed)'.format(self.step // self.interval + 1, self.step))