{"mean_reward": -0.23073623422533274, "std_reward": 0.08735428741571793, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T13:51:49.858355"} |
{"mean_reward": -0.23073623422533274, "std_reward": 0.08735428741571793, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T13:51:49.858355"} |