| {"mean_reward": 270.3548770909039, "std_reward": 12.562950849500833, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-08T10:47:13.859792"} |
| {"mean_reward": 270.3548770909039, "std_reward": 12.562950849500833, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-08T10:47:13.859792"} |