ppo-LunarLander-v3

PPO LunarLander-v3 Agent

This is a trained PPO agent for the LunarLander-v3 environment.

Training Details

• Algorithm: PPO
• Environment: LunarLander-v3
• Mean Reward: 228.59 +/- 54.97

Video of Agent Performance

<video controls autoplay loop>
  <source src="https://huggingface.co/nhankins/ppo-LunarLander-v3/resolve/main/rl-video-episode-0.mp4" type="video/mp4">
</video>

How to use this model

import gymnasium as gym
from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

# Load the model from the Hub
repo_id = "nhankins/ppo-LunarLander-v3"
filename = "ppo-LunarLander-v3.zip"

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

# Create the environment
env = gym.make("LunarLander-v3", render_mode="human") # or rgb_array for recording

obs, info = env.reset()
for _ in range(1000): # Run for 1000 steps
    action, _states = model.predict(obs, deterministic=True)
    obs, rewards, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        obs, info = env.reset()
env.close()