Update README.md

README.md

@@ -30,8 +30,77 @@ 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
+
+# Create the environment
+env = make_vec_env('LunarLander-v2', n_envs=16)
+
+model = PPO(
+    policy = 'MlpPolicy',
+    env = env,
+    n_steps = 1024,
+    batch_size = 64,
+    n_epochs = 4,
+    gamma = 0.999,
+    gae_lambda = 0.98,
+    ent_coef = 0.01,
+    verbose=1)
+
+# Train it for 1,000,000 timesteps
+model.learn(total_timesteps=1000000)
+# Save the model
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
+
+#@title
+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}")
+
+notebook_login()
+!git config --global credential.helper store
+
+import gymnasium as gym
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.vec_env import DummyVecEnv
+from stable_baselines3.common.env_util import make_vec_env
+
+from huggingface_sb3 import package_to_hub
+
+# PLACE the variables you've just defined two cells above
+# Define the name of the environment
+env_id = "LunarLander-v2"
+
+# TODO: Define the model architecture we used
+model_architecture = "PPO"
+
+## Define a repo_id
+## repo_id is the id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
+## CHANGE WITH YOUR REPO ID
+repo_id = "ThomasSimonini/ppo-LunarLander-v2" # Change with your repo id, you can't push with mine 😄
+
+## Define the commit message
+commit_message = "Upload PPO LunarLander-v2 trained agent"
+
+# Create the evaluation env and set the render_mode="rgb_array"
+eval_env = DummyVecEnv([lambda: gym.make(env_id, render_mode="rgb_array")])
+
+# PLACE the package_to_hub function you've just filled here
+package_to_hub(model=model, # Our trained model
+               model_name=model_name, # The name of our trained model
+               model_architecture=model_architecture, # The model architecture we used: in our case PPO
+               env_id=env_id, # Name of the environment
+               eval_env=eval_env, # Evaluation Environment
+               repo_id=repo_id, # id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
+               commit_message=commit_message)
 
-...
 ```