| {"mean_reward": -0.2051507567986846, "std_reward": 0.10450162562085606, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-31T14:07:24.427024"} |
| {"mean_reward": -0.2051507567986846, "std_reward": 0.10450162562085606, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-31T14:07:24.427024"} |