| {"mean_reward": -0.2544624415691942, "std_reward": 0.14836543215808057, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T13:21:08.799328"} |
| {"mean_reward": -0.2544624415691942, "std_reward": 0.14836543215808057, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T13:21:08.799328"} |