Update README.md

README.md

@@ -30,8 +30,46 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
+# In Colab, install packages if required:
+#     gymnasium[box2d]: Contains the LunarLander-v2 environment 🌛
+#     stable-baselines3[extra]: The deep reinforcement learning library.
+#     huggingface_sb3: Additional code for Stable-baselines3 to load and upload models from the Hugging Face 🤗 Hub.
+!apt install swig cmake
+!pip install gymnasium[box2d] stable_baselines3[extra] huggingface-sb3
+
+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
+
+# Create the evaluation environment
+env_id = "LunarLander-v2"
+eval_env = Monitor(gym.make(env_id), filename="./video.mp4")
+
+# Load saved agent
+repo_id = "davidkh/ppo-LunarLander-v2"
+filename = "ppo-LunarLander-v2.zip"
+checkpoint = load_from_hub(repo_id, filename)
+model = PPO.load(checkpoint, print_system_info=True)
+
+# Evaluation
+mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+
+
+# Example use of the trained agent
+observation, info = eval_env.reset()
+for _ in range(1000):
+    eval_env.render()
+    action, _states = model.predict(observation, deterministic=True)
+    observation, rewards, terminated, truncated, info = eval_env.step(action)
+    if terminated or truncated:
+      print("Environment is reset")
+      observation, info = eval_env.reset() 
+
+eval_env.close()
 
 ...
 ```