{"mean_reward": -0.22045150939375163, "std_reward": 0.15473437574314494, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-01T22:42:28.255582"} |
{"mean_reward": -0.22045150939375163, "std_reward": 0.15473437574314494, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-01T22:42:28.255582"} |