{"mean_reward": -0.22709056194871663, "std_reward": 0.1263754776961428, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-16T21:44:43.138059"} |
{"mean_reward": -0.22709056194871663, "std_reward": 0.1263754776961428, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-16T21:44:43.138059"} |