| {"mean_reward": -0.2004163147881627, "std_reward": 0.10637140951240373, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-28T18:26:53.967351"} |
| {"mean_reward": -0.2004163147881627, "std_reward": 0.10637140951240373, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-28T18:26:53.967351"} |