README.md

---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: LunarLander-v2
      type: LunarLander-v2
    metrics:
    - type: mean_reward
      value: 255.80 +/- 42.91
      name: mean_reward
      verified: false
---

# PPO Agent playing LunarLander-v2

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)

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

```bash
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()