| 259 | env = env.env |
| 260 | |
| 261 | def reset(self): |
| 262 | self.summaries_dict['reward'] = -1 |
| 263 | self.summaries_dict['episode_length'] = -1 |
| 264 | self.summaries_dict['total_reward'] = -1 |
| 265 | self.summaries_dict['total_episode_length'] = -1 |
| 266 | self.rewards = [] |
| 267 | env = self.env |
| 268 | if self.episodic_env.was_real_done: |
| 269 | self.summaries_dict['total_reward'] = -1 |
| 270 | self.summaries_dict['total_episode_length'] = -1 |
| 271 | self.total_reward = [] |
| 272 | return self.env.reset() |
| 273 | |
| 274 | def step(self, action): |
| 275 | observation, reward, done, info = self.env.step(action) |