{"mean_reward": -0.226712148450315, "std_reward": 0.09917547471091819, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-31T16:35:29.520124"} |
{"mean_reward": -0.226712148450315, "std_reward": 0.09917547471091819, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-31T16:35:29.520124"} |