PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using Stable-Baselines3.

Evaluation Results

• Environment: LunarLander-v2
• Mean Reward: 259.04 +/- 9.59

Replay Video

Below is a video demonstration of the trained agent playing LunarLander-v2:

Usage (with Stable-Baselines3)

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

repo_id = "Akshaykumar4321/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.zip"

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