Update README.md

README.md

@@ -30,8 +30,26 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+
+# Load the saved statistics
+eval_env = DummyVecEnv([lambda: gym.make("PandaReachDense-v3")])
+eval_env = VecNormalize.load("vec_normalize.pkl", eval_env)
+
+# We need to override the render_mode
+eval_env.render_mode = "rgb_array"
+
+#  do not update them at test time
+eval_env.training = False
+# reward normalization is not needed at test time
+eval_env.norm_reward = False
+
+# Load the agent
+model = A2C.load("a2c-PandaReachDense-v3")
+
+mean_reward, std_reward = evaluate_policy(model, eval_env)
+
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
 
 ...
 ```