{"mean_reward": -0.1718703898601234, "std_reward": 0.0959609713465115, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-30T13:15:03.437475"} |
{"mean_reward": -0.1718703898601234, "std_reward": 0.0959609713465115, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-30T13:15:03.437475"} |