Update README.md

README.md

@@ -26,12 +26,37 @@ 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
 
+Usage (with Stable-baselines3)
+Using this model becomes easy when you have stable-baselines3 and huggingface_sb3 installed:
+
+```
+pip install stable-baselines3
+pip install huggingface_sb3
+```
+Then, you can use the model like this:
 
 ```python
-from stable_baselines3 import ...
+import gym
+
 from huggingface_sb3 import load_from_hub
+from stable_baselines3 import PPO
+from stable_baselines3.common.evaluation import evaluate_policy
 
-...
-```
+checkpoint = load_from_hub(repo_id="Felipe474/ppo-LunarLander-v2", filename="ppo-LunarLander-v2.zip")
+model = PPO.load(checkpoint)
+
+# Evaluate the agent
+eval_env = 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}")
+
+# Watch the agent play
+obs = eval_env.reset()
+for i in range(1000):
+    action, _state = model.predict(obs)
+    obs, reward, done, info = eval_env.step(action)
+    eval_env.render()
+    if done:
+        obs = eval_env.reset()
+eval_env.close()