| {"mean_reward": -0.24669850000000001, "std_reward": 0.12642802672133263, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-19T00:14:39.004739"} |
| {"mean_reward": -0.24669850000000001, "std_reward": 0.12642802672133263, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-19T00:14:39.004739"} |