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)

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.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

# First, we create our environment called LunarLander-v2
env = gym.make("LunarLander-v3")

# 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()


# We create our environment with gym.make("")
env = gym.make("LunarLander-v2")
env.reset()
print("_____OBSERVATION SPACE_____ \n")
print("Observation Space Shape", env.observation_space.shape)
print("Sample observation", env.observation_space.sample()) # Get a random observation



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



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

# We use MultiLayerPerceptron (MLPPolicy) because the input is a vector,
# if we had frames as input we would use CnnPolicy
model = PPO(
    policy='MlpPolicy',
    env=env,
    n_steps=1024,
    batch_size=64,
    n_epochs=20,
    gamma=0.999,
    gae_lambda=0.95,
    ent_coef=0.01,
    learning_rate= 0.0001,
    clip_range=0.2,
    verbose=1
)

# Train it for 1,000,000 timesteps
model.learn(total_timesteps=1000000)
# Save the model
model_name = "ppo-LunarLander-v2"
model.save(model_name)



# Create a new environment for evaluation
#@title
eval_env = Monitor(gym.make("LunarLander-v2"))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")