{"mean_reward": -0.19505456136539578, "std_reward": 0.09145927725100789, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-31T11:25:50.296215"} |
{"mean_reward": -0.19505456136539578, "std_reward": 0.09145927725100789, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-31T11:25:50.296215"} |