| {"mean_reward": -0.21837257063016297, "std_reward": 0.06607982111094438, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-14T07:17:32.224410"} |
| {"mean_reward": -0.21837257063016297, "std_reward": 0.06607982111094438, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-14T07:17:32.224410"} |