piyusharma/PPO-LunarLanding-v3

PPO Agent playing LunarLander-v3

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

Install below libraries

!apt install swig cmake
!pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit1/requirements-unit1.txt
!pip install git+https://github.com/Benjy-D/huggingface_sb3
!sudo apt-get update
!sudo apt-get install -y python3-opengl
!apt install ffmpeg
!apt install xvfb
!pip3 install pyvirtualdisplay

Usage (with Stable-baselines3)

import gymnasium as gym

# First, we create our environment called LunarLander-v3
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("<name_of_the_environment>")
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()) # 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-v3', n_envs=16)

# Define a PPO MlpPolicy architecture
# 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=4, gamma =0.999, gae_lambda=0.98, ent_coef = 0.01, verbose=1)

# Train it for 1,000,000 timesteps
model.learn(total_timesteps=1000000)
# Specify file name for model and save the model to file
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}")

Publish the Model to Hugging Face

import gymnasium as gym
from stable_baselines3.common.vec_env import DummyVecEnv
from stable_baselines3.common.env_util import make_vec_env

from huggingface_sb3 import package_to_hub

## TODO: Define a repo_id
## repo_id is the id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
repo_id = "{Your_HF_Repo_Name}/PPO-LunarLanding-v3" # <--- CHANGE THIS TO YOUR HUGGING FACE USERNAME

# TODO: Define the name of the environment
env_id = "LunarLander-v3"

# Create the evaluation env and set the render_mode="rgb_array"
eval_env = DummyVecEnv([lambda: Monitor(gym.make(env_id, render_mode="rgb_array"))])


# TODO: Define the model architecture we used
model_architecture = "PPO"

## TODO: Define the commit message
commit_message = "Upload PPO Lunar Lander RL Agent"

# method save, evaluate, generate a model card and record a replay video of your agent before pushing the repo to the hub
package_to_hub(model=model, # Our trained model
               model_name=model_name, # The name of our trained model
               model_architecture=model_architecture, # The model architecture we used: in our case PPO
               env_id=env_id, # Name of the environment
               eval_env=eval_env, # Evaluation Environment
               repo_id=repo_id, # id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
               commit_message=commit_message)