| {"mean_reward": -0.1871726145967841, "std_reward": 0.12135876893238, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-10T09:04:44.907799"} |
| {"mean_reward": -0.1871726145967841, "std_reward": 0.12135876893238, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-10T09:04:44.907799"} |