94bfb32cc1
1. add policy.eval() in all test scripts' "watch performance" 2. remove dict return support for collector preprocess_fn 3. add `__contains__` and `pop` in batch: `key in batch`, `batch.pop(key, deft)` 4. exact n_episode for a list of n_episode limitation and save fake data in cache_buffer when self.buffer is None (#184) 5. fix tensorboard logging: h-axis stands for env step instead of gradient step; add test results into tensorboard 6. add test_returns (both GAE and nstep) 7. change the type-checking order in batch.py and converter.py in order to meet the most often case first 8. fix shape inconsistency for torch.Tensor in replay buffer 9. remove `**kwargs` in ReplayBuffer 10. remove default value in batch.split() and add merge_last argument (#185) 11. improve nstep efficiency 12. add max_batchsize in onpolicy algorithms 13. potential bugfix for subproc.wait 14. fix RecurrentActorProb 15. improve the code-coverage (from 90% to 95%) and remove the dead code 16. fix some incorrect type annotation The above improvement also increases the training FPS: on my computer, the previous version is only ~1800 FPS and after that, it can reach ~2050 (faster than v0.2.4.post1).
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
from setuptools import setup, find_packages
|
|
|
|
|
|
setup(
|
|
name='tianshou',
|
|
version='0.2.6',
|
|
description='A Library for Deep Reinforcement Learning',
|
|
long_description=open('README.md', encoding='utf8').read(),
|
|
long_description_content_type='text/markdown',
|
|
url='https://github.com/thu-ml/tianshou',
|
|
author='TSAIL',
|
|
author_email='trinkle23897@gmail.com',
|
|
license='MIT',
|
|
python_requires='>=3.6',
|
|
classifiers=[
|
|
# How mature is this project? Common values are
|
|
# 3 - Alpha
|
|
# 4 - Beta
|
|
# 5 - Production/Stable
|
|
'Development Status :: 3 - Alpha',
|
|
# Indicate who your project is intended for
|
|
'Intended Audience :: Science/Research',
|
|
'Topic :: Scientific/Engineering :: Artificial Intelligence',
|
|
'Topic :: Software Development :: Libraries :: Python Modules',
|
|
# Pick your license as you wish (should match "license" above)
|
|
'License :: OSI Approved :: MIT License',
|
|
# Specify the Python versions you support here. In particular, ensure
|
|
# that you indicate whether you support Python 2, Python 3 or both.
|
|
'Programming Language :: Python :: 3.6',
|
|
'Programming Language :: Python :: 3.7',
|
|
'Programming Language :: Python :: 3.8',
|
|
],
|
|
keywords='reinforcement learning platform pytorch',
|
|
packages=find_packages(exclude=['test', 'test.*',
|
|
'examples', 'examples.*',
|
|
'docs', 'docs.*']),
|
|
install_requires=[
|
|
'gym>=0.15.4',
|
|
'tqdm',
|
|
'numpy',
|
|
'tensorboard',
|
|
'torch>=1.4.0',
|
|
],
|
|
extras_require={
|
|
'dev': [
|
|
'Sphinx',
|
|
'sphinx_rtd_theme',
|
|
'sphinxcontrib-bibtex',
|
|
'flake8',
|
|
'pytest',
|
|
'pytest-cov',
|
|
'ray>=0.8.0',
|
|
],
|
|
'atari': [
|
|
'atari_py',
|
|
'cv2',
|
|
],
|
|
'mujoco': [
|
|
'mujoco_py',
|
|
],
|
|
'pybullet': [
|
|
'pybullet',
|
|
],
|
|
},
|
|
)
|