{"mean_reward": 499.0, "std_reward": 135.31075345293144, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-26T11:31:04.601228"} |
{"mean_reward": 499.0, "std_reward": 135.31075345293144, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-26T11:31:04.601228"} |