{"mean_reward": -0.312194849178195, "std_reward": 0.09527358716265698, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T20:40:47.905424"} |
{"mean_reward": -0.312194849178195, "std_reward": 0.09527358716265698, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T20:40:47.905424"} |