Taranosaurus/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 pyvirtualdisplay import Display
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

virtual_display = Display(visible=0, size=(1400, 900))
virtual_display.start()

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

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:
      # Reset the environment
      print("Environment is reset")
      observation, info = env.reset()


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-v2', n_envs=16)

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-v2"
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}")
...