Update README.md

README.md

@@ -30,8 +30,32 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+import gymnasium as gym
 
-...
-```
+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
+
+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,
+    verbose=1)
+
+model.learn(total_timesteps=1000000)
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
+
+
+eval_env = Monitor(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}")
+```