| {"mean_reward": 626.0, "std_reward": 207.92787210953705, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T11:31:53.815454"} |
| {"mean_reward": 626.0, "std_reward": 207.92787210953705, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T11:31:53.815454"} |