| {"mean_reward": 102.41685680059557, "std_reward": 145.52924764947588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-03T21:07:49.484714"} |
| {"mean_reward": 102.41685680059557, "std_reward": 145.52924764947588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-03T21:07:49.484714"} |