| {"mean_reward": -0.21507313665933908, "std_reward": 0.12754273236877675, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-31T16:48:57.844229"} |
| {"mean_reward": -0.21507313665933908, "std_reward": 0.12754273236877675, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-31T16:48:57.844229"} |