| {"mean_reward": -0.22815865254960954, "std_reward": 0.12744901715977267, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-18T07:19:18.176570"} |
| {"mean_reward": -0.22815865254960954, "std_reward": 0.12744901715977267, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-18T07:19:18.176570"} |