TyurinYuriRost/ppo-LunarLander-v2

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.

Usage (with Stable-baselines3)

To use this model, you need to have stable-baselines3 and huggingface_sb3 installed. You can install them using pip:

pip install stable-baselines3 huggingface_sb3 gymnasium


```python
from huggingface_sb3 import load_from_hub
from stable_baselines3 import PPO
import gymnasium as gym

# Identifier for the repository and model file name
repo_id = "TyurinYuriRost/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.zip"

# Load the model checkpoint from Hugging Face Hub
checkpoint = load_from_hub(repo_id=repo_id, filename=filename)

# Load the PPO model
model = PPO.load(checkpoint)

# Create the environment for evaluation
env = gym.make("LunarLander-v3", render_mode="human")
obs = env.reset()

# Visualize the model's performance
for _ in range(1000):
    action, _states = model.predict(obs)
    obs, rewards, dones, info = env.step(action)
    env.render()
    if dones:
        obs = env.reset()

# Close the environment
env.close()