affordance_seg/collect_dset.py [195:214]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            next_episodes = self.envs.current_episodes()
            envs_to_pause = []
            n_envs = self.envs.num_envs
            for i in range(n_envs):

                if (
                    next_episodes[i]['scene_id'],
                    next_episodes[i]['episode_id'],
                ) in stats_episodes:
                    envs_to_pause.append(i)

                # episode ended
                if not_done_masks[i].item() == 0:

                    episode_stats = dict()
                    episode_stats["reward"] = current_episode_reward[i].item()
                    episode_stats.update(
                        self._extract_scalars_from_info(infos[i])
                    )
                    current_episode_reward[i] = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rl/ppo/ppo_trainer.py [583:602]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            next_episodes = self.envs.current_episodes()
            envs_to_pause = []
            n_envs = self.envs.num_envs
            for i in range(n_envs):

                if (
                    next_episodes[i]['scene_id'],
                    next_episodes[i]['episode_id'],
                ) in stats_episodes:
                    envs_to_pause.append(i)

                # episode ended
                if not_done_masks[i].item() == 0:
                    # pbar.update()
                    episode_stats = dict()
                    episode_stats["reward"] = current_episode_reward[i].item()
                    episode_stats.update(
                        self._extract_scalars_from_info(infos[i])
                    )
                    current_episode_reward[i] = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -