{"mean_reward": -0.2342384062707424, "std_reward": 0.12516612611788105, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-15T09:00:53.721857"} |
{"mean_reward": -0.2342384062707424, "std_reward": 0.12516612611788105, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-15T09:00:53.721857"} |