Update README.md

README.md

@@ -26,12 +26,18 @@ This is a trained model of a **PPO** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)
-TODO: Add your code
-
+Follow to eval the agent locally:
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+repo_id = "Laz4rz/hf-LunarLander-1-ppo" # The repo_id
+filename = "ppo-LunarLander-v2.zip" # The model filename.zip
+
+checkpoint = load_from_hub(repo_id, filename)
+model = PPO.load(checkpoint)
+
+eval_env = Monitor(gym.make("LunarLander-v2"))
+mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
 
 ...
 ```