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

# Create the vectorized environment
env = make_vec_env('LunarLander-v2', n_envs=16)

# Create the PPO model
model = PPO(
    policy = 'MlpPolicy',
    env = env,
    n_steps = 1024,
    batch_size = 64,
    n_epochs = 4,
    gamma = 0.999,
    gae_lambda = 0.98,
    ent_coef = 0.01,
    verbose=1
)

# Train the model for 1,000,000 timesteps
model.learn(total_timesteps=1000000)

# Save the model
model_name = "ppo-LunarLander-v2"
model.save(model_name)

# Create evaluation environment and evaluate the model
eval_env = Monitor(gym.make("LunarLander-v2", render_mode='rgb_array'))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)

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