Update README.md

README.md

@@ -28,6 +28,41 @@ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines
 ## Usage (with Stable-baselines3)
 TODO: Add your code
 
+# Create environment
+env = gym.make('LunarLander-v2')
+# Instantiate the agent
+model = PPO('MlpPolicy', env, verbose=1)
+# Train the agent
+model.learn(total_timesteps=int(2e5))
+
+# TODO: 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(
+    policy = 'MlpPolicy',
+    env = env,
+    n_steps = 4096,
+    batch_size = 128,
+    n_epochs = 8,
+    gamma = 0.999,
+    gae_lambda = 0.98,
+    ent_coef = 0.01,
+    verbose=1)
+
+# TODO: Train it for 1,000,000 timesteps
+model.learn(total_timesteps=2000000)
+# TODO: Specify file name for model and save the model to file
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
+
+# TODO: 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, eval_env, n_eval_episodes=10, deterministic=True)
+# Print the results
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+
 
 ```python
 from stable_baselines3 import ...