| {"mean_reward": -0.13193758949637413, "std_reward": 0.08497300047906312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-18T08:09:09.230155"} |
| {"mean_reward": -0.13193758949637413, "std_reward": 0.08497300047906312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-18T08:09:09.230155"} |