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: 264.51 +/- 16.47
      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) 

This model is trained with the help of [Deep RL Course by HuggingFace](https://huggingface.co/learn/deep-rl-course/unit0/introduction)

## Usage (with Stable-baselines3)
```python
# necessary libraries
import gymnasium as gym

from huggingface_sb3 import load_from_hub, package_to_hub
from huggingface_hub import (
    notebook_login,
)

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor

# Step 1 : Create an environment
env = gym.make("LunarLander-v2")
observation,info = env.reset() # initialize the environment

# Step 2 : Create the model
model = PPO(
    policy = "MlpPolicy", # Multiple Layer Perceptron Policy
    env = env,
    n_steps = 1024,
    batch_size = 64,
    n_epochs = 5,
    gamma = 0.995,
    gae_lambda = 0.98,
    ent_coef = 0.0001,
    clip_range = 0.1,
    verbose = 1
)

# Step 3 : Train the model
model.learn(total_timesteps=2500000,progress_bar = True)

# Step 4 : Evaluation
eval_env = Monitor(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} +/- {std_reward}")
```