| {"mean_reward": 258.0956233433968, "std_reward": 23.77472526645781, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-11T20:21:10.138364"} |
| {"mean_reward": 258.0956233433968, "std_reward": 23.77472526645781, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-11T20:21:10.138364"} |