| {"mean_reward": -0.21466685542836786, "std_reward": 0.11539864944472718, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-06T08:20:50.611773"} |
| {"mean_reward": -0.21466685542836786, "std_reward": 0.11539864944472718, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-06T08:20:50.611773"} |