{"mean_reward": 535.5, "std_reward": 110.3732304501413, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T22:50:27.847143"} |
{"mean_reward": 535.5, "std_reward": 110.3732304501413, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T22:50:27.847143"} |