| {"mean_reward": -0.20391329806298017, "std_reward": 0.08211842999306138, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-27T23:16:07.266946"} |
| {"mean_reward": -0.20391329806298017, "std_reward": 0.08211842999306138, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-27T23:16:07.266946"} |