| {"mean_reward": -0.2271317054517567, "std_reward": 0.09076491722547497, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T15:11:30.930820"} |
| {"mean_reward": -0.2271317054517567, "std_reward": 0.09076491722547497, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T15:11:30.930820"} |