| {"mean_reward": -0.18229326978325844, "std_reward": 0.10414713965295043, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-30T20:16:38.514253"} |
| {"mean_reward": -0.18229326978325844, "std_reward": 0.10414713965295043, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-30T20:16:38.514253"} |