| {"mean_reward": -0.19914039382711052, "std_reward": 0.07879688324468087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-11T01:19:29.375628"} |
| {"mean_reward": -0.19914039382711052, "std_reward": 0.07879688324468087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-11T01:19:29.375628"} |