| {"mean_reward": -0.2118485238868743, "std_reward": 0.12335643665842293, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-12T22:15:36.953191"} |
| {"mean_reward": -0.2118485238868743, "std_reward": 0.12335643665842293, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-12T22:15:36.953191"} |