Update README.md

README.md

@@ -32,5 +32,26 @@ TODO: Add your code
 from stable_baselines3 import ...
 from huggingface_sb3 import load_from_hub
 
-...
+# Create the environment
+env = make_vec_env("LunarLander-v2", n_envs=16)
+
+# Defining the model, we use MultiLayerPerceptron (MLPPolicy) because the input is a vector,
+# if we had frames as input we would use CnnPolicy
+model = PPO(
+    policy="MlpPolicy",
+    env=env,
+    n_steps=1024,
+    batch_size=64,
+    n_epochs=4,
+    gamma=0.999,
+    gae_lambda=0.98,
+    ent_coef=0.01,
+    verbose=1,
+)
+
+# Training the model for 3,000,000 timesteps
+model.learn(total_timesteps=3000000)
+# Save the model
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
 ```