mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-18 21:30:19 +00:00
bb01253261
* init commit tensorboard-integration * Added tb logger to ppo (with output exclusions) * fixed truncated stdout * categorize stdout outputs by tag * separated exclusions from values, added missing logs * saving exclusions as dict instead of list * reformatting, auto run indexing * included renaming suggestions, fixed tests * tb support for sac * linting * moved logging to base class * tb support for td3 * removed histograms, non-verbose output working * modifed changelog * linting * fixed type error * moved logger config to utils * removed episode_rewards log from ppo * Enable tensorboard in tests * Remove unused import * Update logger sub titles * Minor edit for PPO * Update logger and tb log folder * Pass correct logger to Callbacks * updated docs * added tb example image to docs * add support for continuing training in tensorboard * added tensorboard to docs index * added tb test * moved logger config to _setup_learn, updated tests * accessing verbose from base class * Update doc and tests * Rename session -> time * Update version * Update logger truncate * Update types * Remove duplicated code Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
129 lines
4.1 KiB
Python
129 lines
4.1 KiB
Python
import os
|
|
from setuptools import setup, find_packages
|
|
|
|
with open(os.path.join('stable_baselines3', 'version.txt'), 'r') as file_handler:
|
|
__version__ = file_handler.read().strip()
|
|
|
|
|
|
long_description = """
|
|
|
|
# Stable Baselines3
|
|
|
|
Stable Baselines3 is a set of improved implementations of reinforcement learning algorithms in PyTorch. It is the next major version of [Stable Baselines](https://github.com/hill-a/stable-baselines).
|
|
|
|
These algorithms will make it easier for the research community and industry to replicate, refine, and identify new ideas, and will create good baselines to build projects on top of. We expect these tools will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. We also hope that the simplicity of these tools will allow beginners to experiment with a more advanced toolset, without being buried in implementation details.
|
|
|
|
|
|
## Links
|
|
|
|
Repository:
|
|
https://github.com/DLR-RM/stable-baselines3
|
|
|
|
Medium article:
|
|
https://medium.com/@araffin/df87c4b2fc82
|
|
|
|
Documentation:
|
|
https://stable-baselines3.readthedocs.io/en/master/
|
|
|
|
RL Baselines3 Zoo:
|
|
https://github.com/DLR-RM/rl-baselines3-zoo
|
|
|
|
## Quick example
|
|
|
|
Most of the library tries to follow a sklearn-like syntax for the Reinforcement Learning algorithms using Gym.
|
|
|
|
Here is a quick example of how to train and run PPO on a cartpole environment:
|
|
|
|
```python
|
|
import gym
|
|
|
|
from stable_baselines3 import PPO
|
|
|
|
env = gym.make('CartPole-v1')
|
|
|
|
model = PPO('MlpPolicy', env, verbose=1)
|
|
model.learn(total_timesteps=10000)
|
|
|
|
obs = env.reset()
|
|
for i in range(1000):
|
|
action, _states = model.predict(obs, deterministic=True)
|
|
obs, reward, done, info = env.step(action)
|
|
env.render()
|
|
if done:
|
|
obs = env.reset()
|
|
```
|
|
|
|
Or just train a model with a one liner if [the environment is registered in Gym](https://github.com/openai/gym/wiki/Environments) and if [the policy is registered](https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html):
|
|
|
|
```python
|
|
from stable_baselines3 import PPO
|
|
|
|
model = PPO('MlpPolicy', 'CartPole-v1').learn(10000)
|
|
```
|
|
|
|
""" # noqa:E501
|
|
|
|
|
|
setup(name='stable_baselines3',
|
|
packages=[package for package in find_packages()
|
|
if package.startswith('stable_baselines3')],
|
|
package_data={
|
|
'stable_baselines3': ['py.typed', 'version.txt']
|
|
},
|
|
install_requires=[
|
|
'gym>=0.17',
|
|
'numpy',
|
|
'torch>=1.4.0',
|
|
# For saving models
|
|
'cloudpickle',
|
|
# For reading logs
|
|
'pandas',
|
|
# Plotting learning curves
|
|
'matplotlib'
|
|
],
|
|
extras_require={
|
|
'tests': [
|
|
# Run tests and coverage
|
|
'pytest',
|
|
'pytest-cov',
|
|
'pytest-env',
|
|
'pytest-xdist',
|
|
# Type check
|
|
'pytype',
|
|
# Lint code
|
|
'flake8>=3.8'
|
|
],
|
|
'docs': [
|
|
'sphinx',
|
|
'sphinx-autobuild',
|
|
'sphinx-rtd-theme',
|
|
# For spelling
|
|
'sphinxcontrib.spelling',
|
|
# Type hints support
|
|
# 'sphinx-autodoc-typehints'
|
|
],
|
|
'extra': [
|
|
# For render
|
|
'opencv-python',
|
|
# For atari games,
|
|
'atari_py~=0.2.0', 'pillow',
|
|
# Tensorboard support
|
|
'tensorboard'
|
|
]
|
|
},
|
|
description='Pytorch version of Stable Baselines, implementations of reinforcement learning algorithms.',
|
|
author='Antonin Raffin',
|
|
url='https://github.com/DLR-RM/stable-baselines3',
|
|
author_email='antonin.raffin@dlr.de',
|
|
keywords="reinforcement-learning-algorithms reinforcement-learning machine-learning "
|
|
"gym openai stable baselines toolbox python data-science",
|
|
license="MIT",
|
|
long_description=long_description,
|
|
long_description_content_type='text/markdown',
|
|
version=__version__,
|
|
)
|
|
|
|
# python setup.py sdist
|
|
# python setup.py bdist_wheel
|
|
# twine upload --repository-url https://test.pypi.org/legacy/ dist/*
|
|
# twine upload dist/*
|