| {"mean_reward": -0.22986917346715927, "std_reward": 0.0981446807529128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-17T11:31:14.462632"} |
| {"mean_reward": -0.22986917346715927, "std_reward": 0.0981446807529128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-17T11:31:14.462632"} |