| {"mean_reward": -0.2057952607050538, "std_reward": 0.10553459682655403, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T15:09:44.809614"} |
| {"mean_reward": -0.2057952607050538, "std_reward": 0.10553459682655403, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T15:09:44.809614"} |