sighmon/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 huggingface_sb3 import load_from_hub, package_to_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 = make_vec_env('LunarLander-v2', n_envs=16)
model = PPO(
    policy = 'MlpPolicy',
    env = env,
    learning_rate=3e-4,
    n_steps = 2048, # was 1024
    batch_size = 64,
    n_epochs = 10, # was 4
    gamma = 0.99, # was 0.999
    gae_lambda = 0.98,
    ent_coef = 0.01,
    verbose=1)

# Train it for 3,000,000 timesteps
model.learn(total_timesteps=3000000)
# Save the model
model_name = "ppo-LunarLander-v2"
model.save(model_name)

# Create a new environment for evaluation
eval_env = Monitor(gym.make("LunarLander-v2", render_mode='rgb_array'))

# Evaluate the model with 10 evaluation episodes and deterministic=True
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)

# Print the results
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")