| {"mean_reward": 539.5, "std_reward": 104.19812858204317, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-02T21:31:08.601919"} |
| {"mean_reward": 539.5, "std_reward": 104.19812858204317, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-02T21:31:08.601919"} |