{"mean_reward": 258.0, "std_reward": 437.85385689748125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-02T01:01:31.654894"} |
{"mean_reward": 258.0, "std_reward": 437.85385689748125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-02T01:01:31.654894"} |