Cesoft/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)

import gymnasium as gym
from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub
from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.evaluation import evaluate_policy

repo_id = "Cesoft/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.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)

eval_env = Monitor(gym.make("LunarLander-v2", render_mode="human"))
    
mean_reward, std_reward = evaluate_policy(
    model,
    eval_env,
    n_eval_episodes=EVAL_EPISODES,
    deterministic=True,
    render=True
)
eval_env.close()
print(f"mean_reward={mean_reward:.2f} +/- {std_reward} = {mean_reward - std_reward}")
...