{"mean_reward": 789.0, "std_reward": 208.08411760631805, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-19T08:34:55.981626"} |
{"mean_reward": 789.0, "std_reward": 208.08411760631805, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-19T08:34:55.981626"} |