{"mean_reward": -0.22208627443760634, "std_reward": 0.08733036164361489, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T01:59:44.626664"} |
{"mean_reward": -0.22208627443760634, "std_reward": 0.08733036164361489, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T01:59:44.626664"} |