Update README.md

README.md

@@ -25,13 +25,73 @@ 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)
+## Re-train model (with Stable-baselines3)
 TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+# Load a saved LunarLander model from the Hub and retrain
+import gym
+from huggingface_sb3 import load_from_hub, package_to_hub, push_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.evaluation import evaluate_policy
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.vec_env import DummyVecEnv
 
-...
+repo_id = "thien1892/LunarLander-v2-ppo-v5"
+filename = "ppo-LunarLander-v2.zip" # The model filename.zip
+checkpoint = load_from_hub(repo_id, filename)
+
+myenv = make_vec_env('LunarLander-v2', n_envs=16)
+custom_objects = {
+            "learning_rate": 1e-5,
+            "clip_range": lambda _: 0.15,
+}
+model = PPO.load(checkpoint, reset_num_timesteps=True, print_system_info=True,custom_objects = custom_objects, env = myenv)
+
+# Train it for 1,000,000 timesteps
+model.learn(total_timesteps=1000000)
+# Save the model
+model_name = "ppo-LunarLander-v2-5m"
+model.save(model_name)
+
+# Evaluate
+eval_env = 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}")
+```
+
+## Pust to HF hub
+
+```python
+notebook_login()
+!git config --global credential.helper store
 ```
+
+```
+## 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
+repo_id = "thien1892/LunarLander-v2-ppo-5m"
+
+# TODO: Define the name of the environment
+env_id = "LunarLander-v2"
+
+# Create the evaluation env
+eval_env = DummyVecEnv([lambda: gym.make(env_id)])
+
+
+# TODO: Define the model architecture we used
+model_architecture = "PPO"
+
+## TODO: Define the commit message
+commit_message = "Upload PPO LunarLander-v2 trained agent"
+
+# method save, evaluate, generate a model card and record a replay video of your agent before pushing the repo to the hub
+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)
+```