Add usage

README.md

@@ -25,6 +25,43 @@ model-index:
   
 ## Usage (with Stable-baselines3)
 
+```python
+from huggingface_sb3 import load_from_hub
+from stable_baselines3 import PPO
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.evaluation import evaluate_policy
+
+# Download checkpoint
+checkpoint = load_from_hub("araffin/ppo-LunarLander-v2", "ppo-LunarLander-v2.zip")
+# Load the model
+model = PPO.load(checkpoint)
+
+env = make_vec_env("LunarLander-v2", n_envs=1)
+
+# Evaluate
+print("Evaluating model")
+mean_reward, std_reward = evaluate_policy(
+    model,
+    env,
+    n_eval_episodes=20,
+    deterministic=True,
+)
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
+
+# Start a new episode
+obs = env.reset()
+
+try:
+    while True:
+        action, _states = model.predict(obs, deterministic=True)
+        obs, rewards, dones, info = env.step(action)
+        env.render()
+except KeyboardInterrupt:
+    pass
+```
+
+## Training code (with SB3)
+
 ```python
 from stable_baselines3 import PPO
 from stable_baselines3.common.env_util import make_vec_env