| {"mean_reward": -0.18034404339268803, "std_reward": 0.07252318449700859, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-16T03:09:03.198349"} |
| {"mean_reward": -0.18034404339268803, "std_reward": 0.07252318449700859, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-16T03:09:03.198349"} |