{"mean_reward": -0.2244686469435692, "std_reward": 0.1293663605356438, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-15T20:47:26.919485"} |
{"mean_reward": -0.2244686469435692, "std_reward": 0.1293663605356438, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-15T20:47:26.919485"} |