{"mean_reward": -0.2045908212661743, "std_reward": 0.10147378744392842, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T20:57:34.166326"} |
{"mean_reward": -0.2045908212661743, "std_reward": 0.10147378744392842, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T20:57:34.166326"} |