| {"mean_reward": 265.99858570000004, "std_reward": 19.826224970977027, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T12:21:30.347330"} |
| {"mean_reward": 265.99858570000004, "std_reward": 19.826224970977027, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T12:21:30.347330"} |