kongacute's picture
Upload PPO LunarLander-v2 trained agent hyperparameter tunning by optuna
ddf7dfd
raw
history blame
163 Bytes
{"mean_reward": -856.1900397393795, "std_reward": 384.340459532218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:38:41.418759"}