Update README.md

README.md

@@ -26,12 +26,49 @@ 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 ...
+import gymnasium
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.monitor import Monitor
 from huggingface_sb3 import load_from_hub
 
+
+# Create the environment
+env = make_vec_env('LunarLander-v2', n_envs=16)
+
+# Define a PPO MlpPolicy architecture
+# We use MultiLayerPerceptron (MLPPolicy) because the input is a vector,
+# if we had frames as input we would use CnnPolicy
+model = PPO(
+    "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)
+
+# Train it for 1,000,000 timesteps
+model.learn(total_timesteps=1000000)
+# Specify file name for model and save the model to file
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
+
+# Evaluate the agent
+# Create a new environment for evaluation
+eval_env = Monitor(gym.make("LunarLander-v2"))
+
+# Evaluate the model with 10 evaluation episodes and deterministic=True
+mean_reward, std_reward = evaluate_policy(model=model, env=eval_env, n_eval_episodes=10, deterministic=True) 
+
+# Print the results
+print(mean_reward)
+print(std_reward)
 ...
 ```