kwplayground/learning-basics

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

from huggingface_sb3 import load_from_hub, package_to_hub
from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor

env = gym.make('LunarLander-v2')


model = PPO(
    policy = 'MlpPolicy',
    env = env,
    n_steps = 1000,
    batch_size = 64,
    n_epochs = 4,
    gamma = 0.99,
    verbose=1)

model.learn(total_timesteps=10000)
model_name = "ppo-LunarLander-v2"
model.save(model_name)
eval_env =  Monitor(gym.make(
    "LunarLander-v2"
))

mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")

...