| {"mean_reward": -0.16944928038865328, "std_reward": 0.12044269494052763, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T16:58:09.740361"} |
| {"mean_reward": -0.16944928038865328, "std_reward": 0.12044269494052763, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T16:58:09.740361"} |