{"mean_reward": -0.18027256671339273, "std_reward": 0.09543744829923079, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-31T14:13:05.851476"} |
{"mean_reward": -0.18027256671339273, "std_reward": 0.09543744829923079, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-31T14:13:05.851476"} |