update readme

README.md

@@ -30,8 +30,30 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
+from stable_baselines3 import PPO
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.evaluation import evaluate_policy
 from huggingface_sb3 import load_from_hub
 
-...
+# Download the model checkpoint
+repo_id = "DarkRodry/ppo-LunarLander-v2" 
+filename = "base_tutorial_model.zip" 
+model_checkpoint = load_from_hub(repo_id, filename)
+
+
+# Create a vectorized environment
+env = make_vec_env("LunarLander-v2", n_envs=1)
+
+# Load the model
+model = PPO.load(model_checkpoint, env=env)
+
+# Evaluate
+print("Evaluating model")
+mean_reward, std_reward = evaluate_policy(
+    model,
+    env,
+    n_eval_episodes=30,
+    deterministic=True,
+)
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward}")
 ```