Update README.md

README.md

@@ -30,8 +30,29 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
 
+from stable_baselines3 import PPO
+from huggingface_sb3 import load_from_hub, package_to_hub
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+
+env_id = "PandaReachDense-v3"
+env = gym.make(env_id)
+env = make_vec_env(env_id, n_envs=4)
+env = VecNormalize(env, training=True, norm_obs=True, norm_reward=True, gamma=0.5, epsilon=1e-10, norm_obs_keys=None)
+
+model =  PPO("MultiInputPolicy", env, verbose=1)
+model.learn(1_000_000)
+
+eval_env = DummyVecEnv([lambda: gym.make("PandaReachDense-v3")])
+eval_env = VecNormalize.load("vec_normalize.pkl", eval_env)
+eval_env.render_mode = "rgb_array"
+eval_env.training = False
+# reward normalization is not needed at test time
+eval_env.norm_reward = False
+
+
+model = PPO.load("Slay-PandaReachDense-v3")
+mean_reward, std_reward = evaluate_policy(model, eval_env)
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
 ...
 ```