{"mean_reward": -0.2340781764127314, "std_reward": 0.07296314285498133, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-27T14:49:51.307983"} |
{"mean_reward": -0.2340781764127314, "std_reward": 0.07296314285498133, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-27T14:49:51.307983"} |