{"mean_reward": -0.21332493051886559, "std_reward": 0.13031362221197237, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-07T15:43:17.261528"} |
{"mean_reward": -0.21332493051886559, "std_reward": 0.13031362221197237, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-07T15:43:17.261528"} |