| {"mean_reward": -0.22374816350638865, "std_reward": 0.1641865200891069, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-14T19:23:45.467766"} |
| {"mean_reward": -0.22374816350638865, "std_reward": 0.1641865200891069, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-14T19:23:45.467766"} |