v0.0.3

CHANGELOG.md

@@ -1,20 +1,54 @@
-2023.9.21(v0.0.2)
+2023.12.07 (v0.0.3)
+- env: MiniGrid env (#110)
+- env: Bsuite env (#110)
+- env: GoBigger env (#39)
+- algo: RND+MuZero (#110)
+- algo: Sampled AlphaZero (#141)
+- algo: Multi-Agent MuZero/EfficientZero (#39)
+- feature: add ctree version of mcts in alphazero (#142)
+- feature: upgrade the dependency on gym with gymnasium (#150)
+- feature: add agent class to support LightZero's HuggingFace Model Zoo (#163)
+- feature: add recent MCTS-related papers in readme (#159)
+- feature: add muzero config for connect4 (#107)
+- feature: added CONTRIBUTING.md (#119)
+- feature: added .gitpod.yml and .gitpod.Dockerfile (#123)
+- feature: added contributors subsection in README (#132) 
+- feature: added CODE_OF_CONDUCT.md (#127)
+- polish: refine comments and render_eval configs for various common envs (#154) (#161)
+- polish: polish action_type and env_type, fix test.yml, fix unittest (#160)
+- polish: update env and algo tutorial doc (#106)
+- polish: polish gomoku env (#141)
+- polish: add random_policy support for continuous env (#118)
+- polish: polish simulation method of ptree_az (#120)
+- polish: polish comments of game_segment_to_array
+- fix: fix render method for various common envs (#154) (#161)
+- fix: fix gumbel muzero collector bug, fix gumbel typo (#144)
+- fix: fix assert bug in game_segment.py (#138)
+- fix: fix visit_count_distributions name in muzero_evaluator
+- fix: fix mcts and alphabeta bot unittest (#120)
+- fix: fix typos in ptree_mz.py (#113)
+- fix: fix root_sampled_actions_tmp shape bug in sez ptree
+- fix: fix policy utils unittest
+- fix: fix typo in readme and add a 'back to top' button in readme (#104) (#109) (#111)
+- style: add nips2023 paper link
+
+2023.09.21 (v0.0.2)
 - env: MuJoCo env (#50)
 - env: 2048 env (#64)
 - env: Connect4 env (#63)
 - algo: Gumbel MuZero (#22)
 - algo: Stochastic MuZero (#64)
-- polish: polish mcts and ptree_az (#57) (#61)
-- polish: polish readme (#36) (#47) (#51) (#77) (#95) (#96)
-- polish: update paper notes (#89) (#91)
-- polish: polish model and configs (#26) (#27) (#50)
 - feature: add Dockerfile and its usage instructions (#95)
 - feature: add doc about how to customize envs and algos (#78)
 - feature: add pytorch ddp support (#68)
 - feature: add eps greedy and random collect option in train_muzero_entry (#54)
 - feature: add atari visualization option (#40)
 - feature: add log_buffer_memory_usage utils (#30)
+- polish: polish mcts and ptree_az (#57) (#61)
+- polish: polish readme (#36) (#47) (#51) (#77) (#95) (#96)
+- polish: update paper notes (#89) (#91)
+- polish: polish model and configs (#26) (#27) (#50)
 - fix: fix priority bug in muzero collector (#74)
 - style: update github action (#71) (#72) (#73) (#81) (#83) (#84) (#90)
 
-2023.4.14(v0.0.1)
+2023.04.14 (v0.0.1)

README.md

@@ -27,7 +27,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/LightZero)](https://github.com/opendilab/LightZero/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/LightZero)](https://github.com/opendilab/LightZero/blob/master/LICENSE)
 
-Updated on 2023.09.21 LightZero-v0.0.2
+Updated on 2023.12.07 LightZero-v0.0.3
 
 > LightZero is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL). 
 

README.zh.md

@@ -27,7 +27,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/LightZero)](https://github.com/opendilab/LightZero/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/LightZero)](https://github.com/opendilab/LightZero/blob/master/LICENSE)
 
-Updated on 2023.09.21 LightZero-v0.0.2
+最近更新于 2023.12.07 LightZero-v0.0.3
 
 > LightZero 是一个轻量、高效、易懂的 MCTS+RL 开源算法库。
 

lzero/config/meta.py

@@ -7,7 +7,7 @@
 __TITLE__ = "LightZero"
 
 #: Version of this project.
-__VERSION__ = "0.0.2"
+__VERSION__ = "0.0.3"
 
 #: Short description of the project, will be included in ``setup.py``.
 __DESCRIPTION__ = 'A lightweight and efficient MCTS/AlphaZero/MuZero algorithm toolkits.'

setup.py

@@ -15,7 +15,6 @@
 
 import numpy as np
 from setuptools import find_packages, Extension
-# from setuptools.command.build_ext import build_ext
 from Cython.Build import cythonize  # this line should be after 'from setuptools import find_packages'
 
 here = os.path.abspath(os.path.dirname(__file__))
@@ -25,19 +24,6 @@ def _load_req(file: str):
     with open(file, 'r', encoding='utf-8') as f:
         return [line.strip() for line in f.readlines() if line.strip()]
 
-
-# class custom_build_ext(build_ext):
-#     def build_extensions(self):
-#         # Override the compiler executables. Importantly, this
-#         # removes the "default" compiler flags that would
-#         # otherwise get passed on to the compiler, i.e.,
-#         # distutils.sysconfig.get_var("CFLAGS").
-#         self.compiler.set_executable("compiler_so", "g++")
-#         self.compiler.set_executable("compiler_cxx", "g++")
-#         self.compiler.set_executable("linker_so", "g++")
-#         build_ext.build_extensions(self)
-
-
 requirements = _load_req('requirements.txt')
 
 _REQ_PATTERN = re.compile('^requirements-([a-zA-Z0-9_]+)\\.txt$')
@@ -85,9 +71,8 @@ def find_cython_extensions(path=None):
 
 setup(
     name='LightZero',
-    version='0.0.2',
+    version='0.0.3',
     description='A lightweight and efficient MCTS/AlphaZero/MuZero algorithm toolkits.',
-    # long_description=readme,
     long_description_content_type='text/markdown',
     author='opendilab',
     author_email='[email protected]',
@@ -115,7 +100,6 @@ def find_cython_extensions(path=None):
             linetrace=_LINETRACE,
         ),
     ),
-    # cmdclass={"build_ext": custom_build_ext},
     classifiers=[
         'Development Status :: 5 - Production/Stable',
         "Intended Audience :: Science/Research",