| {"mean_reward": -0.2273880454711616, "std_reward": 0.10433230731952914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T00:19:12.293399"} |
| {"mean_reward": -0.2273880454711616, "std_reward": 0.10433230731952914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T00:19:12.293399"} |