Update README.md

README.md

@@ -26,12 +26,31 @@ 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 ...
+import gymnasium as gym
+from stable_baselines3 import PPO
+from stable_baselines3.common.monitor import Monitor
+from stable_baselines3.common.evaluation import evaluate_policy
 from huggingface_sb3 import load_from_hub
 
-...
+repo_id = "JohnnyBoy00/ppo-LunarLander-v2"
+filename = "ppo-LunarLander-v2.zip"
+
+# The model was trained with Python 3.8, which uses Pickle Protocol 5.
+# However, Python 3.6 and 3.7 use Pickle Protocol 4.
+# Thus, in order to ensure compatibility, it is necessary to:
+# 1. Install pickle5 (we done it at the beginning of the colab);
+# 2. Create a custom empty object, which is passed as a 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)
+
+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}")
 ```