{"mean_reward": -0.18175507336854935, "std_reward": 0.2618982376300379, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-16T05:31:20.166952"} |
{"mean_reward": -0.18175507336854935, "std_reward": 0.2618982376300379, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-16T05:31:20.166952"} |