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: 249.81 +/- 23.73
      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)
```python
from stable_baselines3 import PPO
from stable_baselines3.common.envs import LunarLander
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.evaluation import evaluate_policy

# Create the LunarLander environment
env = LunarLander()

# Vectorize the environment for parallel training
vec_env = make_vec_env('LunarLander-v2', n_envs=16)

# Instantiate the PPO agent
model = PPO("MlpPolicy", vec_env, verbose=1)

# Train the agent
model.learn(total_timesteps=int(2e5))

# Evaluate the trained agent
eval_env = LunarLander()
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")

# Save the trained model
model_name = "ppo-LunarLander-v2"
model.save(model_name)

# Package and upload the model to the Hub
from huggingface_sb3 import package_to_hub
package_to_hub(model=model,
               model_name=model_name,
               model_architecture="PPO",
               env_id="LunarLander-v2",
               eval_env=eval_env,
               repo_id="your-username/ppo-LunarLander-v2",
               commit_message="Upload PPO LunarLander-v2 trained agent")
```

Ensure to replace `"your-username"` with your Hugging Face username.