{"mean_reward": -0.19439311381429433, "std_reward": 0.11528731142243182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-22T07:23:44.852066"} |
{"mean_reward": -0.19439311381429433, "std_reward": 0.11528731142243182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-22T07:23:44.852066"} |