README.md

---
license: mit
language:
- en
library_name: stable-baselines3
tags:
- reinforcement-learning
- LunarLander-v3
model-index:
- name: PPO
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: LunarLander-v3
      type: LunarLander-v3
    metrics:
    - type: mean_reward
      value: 220.66 +/- 93.99
      name: mean_reward
      verified: false
---
# **PPO** Agent playing **LunarLander-v3**
- [Github Repository](https://github.com/kuds/rl-lunar-lander)
- [Google Colab Notebook](https://colab.research.google.com/github/kuds/rl-lunar-lander/blob/main/%5BLunar%20Lander%5D%20Proximal%20Policy%20Optimization%20(PPO).ipynb)
- [Finding Theta - Blog Post](https://www.findingtheta.com/blog/comparing-how-ppo-sac-and-dqn-perform-on-gymnasiums-lunar-lander)


Then, you can load the model using the following Python code:

```python
import gymnasium as gym
from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env

# Load the trained model
model = PPO.load("best-model.zip")

# Create the environment
env = make_vec_env("LunarLander-v3", n_envs=1)

# Reset the environment
obs, info = env.reset()

# Enjoy the trained agent
for _ in range(1000):
    action, _states = model.predict(obs, deterministic=True)
    obs, rewards, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        obs, info = env.reset()
    env.render()
env.close()
```

### Hugging Face Hub

You can also use the Hugging Face Hub to load the model. First, you need to install the Hugging Face Hub library:

```bash
pip install huggingface_hub
```

Then, you can load the model from the hub using the following code:

```python
from huggingface_hub import hf_hub_download
import torch as th
import gymnasium as gym
from stable_baselines3 import PPO

# Download the model from the Hub
model_path = hf_hub_download(repo_id="kuds/lunar-lander-ppo", filename="best-model.zip")

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

# Create the environment
env = make_vec_env("LunarLander-v3", n_envs=1)

# Enjoy the trained agent
obs = env.reset()
for i in range(1000):
    action, _states = model.predict(obs, deterministic=True)
    obs, rewards, dones, info = env.step(action)
    env.render("human")
```