{"mean_reward": -0.2272780431434512, "std_reward": 0.0997066389784176, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T06:51:12.549089"} |
{"mean_reward": -0.2272780431434512, "std_reward": 0.0997066389784176, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T06:51:12.549089"} |