| {"mean_reward": 397.0, "std_reward": 122.21292893961751, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-22T04:28:53.768272"} |
| {"mean_reward": 397.0, "std_reward": 122.21292893961751, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-22T04:28:53.768272"} |