updating ReadMe

README.md

@@ -26,12 +26,38 @@ 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
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+import gym
+
+from huggingface_sb3 import load_from_hub, package_to_hub, push_to_hub
+from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.env_util import make_vec_env
+
+# Create the environment
+env = make_vec_env('LunarLander-v2', n_envs=16)
+
+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,
+    learning_rate=0.0004,
+    verbose=1)
+
+# Train it for 3,000,000 timesteps
+model.learn(total_timesteps=3000000)
+# Save the model
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
 
 ...
 ```