| {"mean_reward": 0.5202, "std_reward": 0.28504483857807356, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T20:11:19.680936"} |
| {"mean_reward": 0.5202, "std_reward": 0.28504483857807356, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T20:11:19.680936"} |