| {"mean_reward": -0.2615303416736424, "std_reward": 0.13682579697449893, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-16T04:25:03.560403"} |
| {"mean_reward": -0.2615303416736424, "std_reward": 0.13682579697449893, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-16T04:25:03.560403"} |