{"mean_reward": 550.0, "std_reward": 68.26419266350405, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-21T19:11:14.889675"} |
{"mean_reward": 550.0, "std_reward": 68.26419266350405, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-21T19:11:14.889675"} |