| {"mean_reward": -0.7187702842056751, "std_reward": 1.2057652510034347, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-14T11:44:09.203038"} |
| {"mean_reward": -0.7187702842056751, "std_reward": 1.2057652510034347, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-14T11:44:09.203038"} |