{"mean_reward": -0.24546841587871313, "std_reward": 0.18165261927220622, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-18T21:08:41.734335"} |
{"mean_reward": -0.24546841587871313, "std_reward": 0.18165261927220622, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-18T21:08:41.734335"} |