| {"mean_reward": -0.18226835187524557, "std_reward": 0.09930353893307248, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T16:22:26.602081"} |
| {"mean_reward": -0.18226835187524557, "std_reward": 0.09930353893307248, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T16:22:26.602081"} |