Add code

8233a46 about 1 year ago

4.98 kB

	---
	library_name: stable-baselines3
	tags:
	- LunarLander-v2
	- deep-reinforcement-learning
	- reinforcement-learning
	- stable-baselines3
	model-index:
	- name: PPO
	results:
	- task:
	type: reinforcement-learning
	name: reinforcement-learning
	dataset:
	name: LunarLander-v2
	type: LunarLander-v2
	metrics:
	- type: mean_reward
	value: 290.32 +/- 15.84
	name: mean_reward
	verified: false
	---

	# PPO Agent playing LunarLander-v2
	This is a trained model of a PPO agent playing LunarLander-v2
	using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).

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

	## Usage (with Stable-baselines3)


	```python
	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}")
	...
	```