| {"mean_reward": -0.2308511869981885, "std_reward": 0.10697507173436531, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-31T17:07:32.181061"} |
| {"mean_reward": -0.2308511869981885, "std_reward": 0.10697507173436531, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-31T17:07:32.181061"} |