| {"mean_reward": 265.9860526717768, "std_reward": 15.105332893011974, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-08T20:57:32.758340"} |
| {"mean_reward": 265.9860526717768, "std_reward": 15.105332893011974, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-08T20:57:32.758340"} |