pr0mila-gh0sh/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)

Install Packages

!pip install shimmy
!pip install gymnasium==0.28.0

Run the code

from gymnasium.wrappers import RecordVideo, RecordEpisodeStatistics
from huggingface_sb3 import load_from_hub
from stable_baselines3 import PPO

repo_id = "promila-2024/ppo-LunarLander-v2" # The repo_id
filename = "ppo-LunarLander-v2.zip" # The model filename.zip

custom_objects = {
            "learning_rate": 0.0,
            "lr_schedule": lambda _: 0.0,
            "clip_range": lambda _: 0.0,
}

checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)