HugBot/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.

Colab

https://colab.research.google.com/github/huggingface/deep-rl-class/blob/master/notebooks/unit1/unit1.ipynb#scrollTo=PAEVwK-aahfx

Usage (with Stable-baselines3)

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

# We create our environment with gym.make("<name_of_the_environment>")
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)
# TODO: 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('MlpPolicy', env, verbose=1)
# TODO: Train it for 1,000,000 timesteps
model.learn(total_timesteps=int(2e6))

# TODO: Specify file name for model and save the model to file
model_name = "ppo-LunarLander-v1"
model.save(model_name)

# TODO: Evaluate the agent
# Create a new environment for evaluation
eval_env = Monitor(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}")

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 = "HugBot/ppo-LunarLander-v2"

# TODO: Define the name of the environment
env_id = "LunarLander-v2"

# 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 LunarLander-v2 trained 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)

from huggingface_sb3 import load_from_hub
repo_id = "HugBot/ppo-LunarLander-v2" # The repo_id
filename = "ppo-LunarLander-v1.zip" # The model filename.zip

# When the model was trained on Python 3.8 the pickle protocol is 5
# But Python 3.6, 3.7 use protocol 4
# In order to get compatibility we need to:
# 1. Install pickle5 (we done it at the beginning of the colab)
# 2. Create a custom empty object we pass as parameter to PPO.load()
custom_objects = {
            "learning_rate": 0.0,
            "lr_schedule": lambda _: 0.0,
            "clip_range": lambda _: 0.0,
}

checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)

#@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}")
...