lushy/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)

The code below downloads the model and runs 3 episodes and saves the videos to "lunar_lander_videos/".

import gymnasium as gym
from stable_baselines3 import PPO
from huggingface_hub import hf_hub_download
import imageio
import os

# Configuration
MODEL_REPO = "lushy/ppo-LunarLander-v2"
OUTPUT_DIR = "lunar_lander_videos"
NUM_EPISODES = 3
VIDEO_FPS = 30

# Create output directory
os.makedirs(OUTPUT_DIR, exist_ok=True)

# Download and load model from Hugging Face
print("Loading model from Hugging Face...")
model_path = hf_hub_download(repo_id=MODEL_REPO, filename="ppo-LunarLander-v2.zip")
model = PPO.load(model_path)

# Create environment
print("Creating Lunar Lander environment...")
env = gym.make("LunarLander-v3", render_mode="rgb_array")

# Record all episodes into one list
all_frames = []

for episode in range(NUM_EPISODES):
    print(f"\nRecording episode {episode + 1}/{NUM_EPISODES}...")
    
    observation, info = env.reset()
    episode_reward = 0
    done = False
    
    while not done:
        # Render frame
        frame = env.render()
        if frame is not None:
            # Resize frame to 1080p
            import cv2
            frame = cv2.resize(frame, (VIDEO_WIDTH, VIDEO_HEIGHT))
            all_frames.append(frame)
        
        # Get action from model
        action, _ = model.predict(observation, deterministic=True)
        
        # Step environment
        observation, reward, terminated, truncated, info = env.step(action)
        episode_reward += reward
        done = terminated or truncated
    
    print(f"Episode {episode + 1} reward: {episode_reward:.2f}")

# Save all episodes as one video
video_path = os.path.join(OUTPUT_DIR, "lunar_lander_all_episodes.mp4")
print(f"\nSaving combined video to {video_path}...")
imageio.mimsave(video_path, all_frames, fps=VIDEO_FPS, codec='libx264', pixelformat='yuv420p')

env.close()
print(f"Video saved to {OUTPUT_DIR}/lunar_lander_all_episodes.mp4")