Update README.md

README.md

@@ -25,13 +25,31 @@ model-index:
 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 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
 
+repo_id = "Anish13/ppo-LunarLander-v2" # The repo_id
+filename = "ppo-LunarLander-v2.zip" 
+
+custom_objects = {
+            "learning_rate": 0.0,
+            "lr_schedule": lambda _: 0.0,
+            "clip_range": lambda _: 0.0,
+}
+
+checkpoint = load_from_hub(repo_id, filename)
+model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
+
+
+
+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}")
+
 ...
 ```