{"mean_reward": 591.0, "std_reward": 265.13015671552716, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-12T06:12:40.454410"} |
{"mean_reward": 591.0, "std_reward": 265.13015671552716, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-12T06:12:40.454410"} |