yssnn04/ppo-LunarLander-v3

PPO Agent playing LunarLander-v3

This is a trained model of a PPO agent playing LunarLander-v3 using the stable-baselines3 library.

Metrics

The trained PPO agent achieves a mean reward of 258.34 ± 18.85 on LunarLander-v3. This means it consistently lands successfully, demonstrating both high performance and stability across multiple episodes.

Usage (with Stable-baselines3)

from huggingface_sb3 import load_from_hub, package_to_hub
from huggingface_hub import notebook_login
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
import gymnasium as gym

env = gym.make("LunarLander-v3")
observation, info = env.reset()

for _ in range(20):
  action = env.action_space.sample()
  print("Action taken:", action)

  observation, reward, terminated, truncated, info = env.step(action)

  if terminated or truncated:
      print("Environment is reset")
      observation, info = env.reset()

env.close()

env = gym.make("LunarLander-v3")
env.reset()
print("_____OBSERVATION SPACE_____ \n")
print("Observation Space Shape", env.observation_space.shape)
print("Sample observation", env.observation_space.sample())

print("\n _____ACTION SPACE_____ \n")
print("Action Space Shape", env.action_space.n)
print("Action Space Sample", env.action_space.sample()) # Take a random action

env = make_vec_env('LunarLander-v3', n_envs=16)

env = gym.make('LunarLander-v3')
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)
model.learn(total_timesteps=1000000)
model_name = "ppo-LunarLander-v3"
model.save(model_name)

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(f"mean_reward={mean_reward:.2f} +/- {std_reward}")