update usage instructions

README.md

@@ -26,12 +26,37 @@ This is a trained model of a **PPO (Proximal Policy Optimization)** agent playin
 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 huggingface_sb3 import load_from_hub
+import gymnasium
+
+from huggingface_sb3 import load_from_hub, package_to_hub
+from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.
+
+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
+
+repo_id = "xXrobroXx/ppo-LunarLander-v2" # The repo_id
+filename = "ppo-LunarLander-v2.zip" # The model filename.zip
+
+# When the model was trained on Python 3.8 the pickle protocol is 5
+# But Python 3.6, 3.7 use protocol 4
+# In order to get compatibility we need to:
+# 1. Install pickle5 
+# 2. Create a custom empty object we pass as parameter to PPO.load()
+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)
 
-...
+# evaluate model in test environment
+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}")
 ```