Toffee0705/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)

TODO: Add your code

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

import gymnasium as gym

# First, we create our environment called LunarLander-v2
env = gym.make("LunarLander-v2")

# Then we reset this environment
observation, info = env.reset()

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

  # Do this action in the environment and get
  # next_state, reward, terminated, truncated and info
  observation, reward, terminated, truncated, info = env.step(action)
  
  # If the game is terminated (in our case we land, crashed) or truncated (timeout)
  if terminated or truncated:
      # Reset the environment
      print("Environment is reset")
      observation, info = env.reset()

env.close()

# Create the environment
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)

# TODO: Train it for 1,000,000 timesteps
model.learn(total_timesteps=1000000)

# TODO: Specify file name for model and save the model to file
model_name = "ppo-LunarLander-v2"
model.save(model_name)

# TODO: Evaluate the agent
# Create a new environment for evaluation
eval_env = gym.make("LunarLander-v2")

# 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}")

...