{"mean_reward": -0.21121751349419354, "std_reward": 0.09971964511669015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T11:23:20.218362"} |
{"mean_reward": -0.21121751349419354, "std_reward": 0.09971964511669015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T11:23:20.218362"} |