Updated the usage code

README.md

@@ -26,12 +26,33 @@ 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 ...
+# Usage code
+import gymnasium as gym
 from huggingface_sb3 import load_from_hub
+from stable_baselines3 import PPO
+from stable_baselines3.common.vec_env import DummyVecEnv
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.monitor import Monitor
 
-...
+repo_id = "VinayHajare/ppo-LunarLander-v2"
+filename = "ppo-LunarLander-v2.zip"
+eval_env = DummyVecEnv([lambda: Monitor(gym.make("LunarLander-v2", render_mode="rgb_array"))])
+
+checkpoint = load_from_hub(repo_id, filename)
+model = PPO.load(checkpoint,env=eval_env,print_system_info=True)
+
+#eval_env = DummyVecEnv([lambda: Monitor(gym.make("LunarLander-v2", render_mode="rgb_array"))])
+mean_reward, std_reward = evaluate_policy(model,eval_env, n_eval_episodes=10, deterministic=True)
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+
+# Enjoy trained agent
+vec_env = model.get_env()
+obs = vec_env.reset()
+for _ in range(1000):
+    action, _states = model.predict(obs, deterministic=True)
+    obs, rewards, dones, info = vec_env.step(action)
+    vec_env.render("human")
 ```