| {"mean_reward": -0.22270322404801846, "std_reward": 0.06705670685303013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-26T11:32:14.676135"} |
| {"mean_reward": -0.22270322404801846, "std_reward": 0.06705670685303013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-26T11:32:14.676135"} |