Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feature(wrh): add continuous action space in mt for unizero. #271

Open
wants to merge 26 commits into
base: dev-unizero-multitask-v2
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
c1da960
polish(pu): polish readme using colorful icons
puyuan1996 Jul 12, 2024
fdd414c
fix(pu): fix lightzero versions
puyuan1996 Jul 12, 2024
83f10f0
fix(pu): fix empty_keys_values in init_infer
dyyoungg Jul 14, 2024
e11cf12
polish(pu): polish documentation in readme
puyuan1996 Jul 15, 2024
d2f5ba8
Merge branch 'main' of https://github.com/opendilab/LightZero
puyuan1996 Jul 15, 2024
230a4a5
feature(pu): add lightzero sphinx docs (#237)
puyuan1996 Jul 15, 2024
8c691d6
polish(pu): polish documentation structure
puyuan1996 Jul 15, 2024
032825f
feature(wrh): Add Harmony Dream loss balance in MuZero (#242)
ruiheng123 Jul 16, 2024
a44a2bf
polish(pu): polish documentation
puyuan1996 Jul 16, 2024
a0bf161
Merge branch 'main' of https://github.com/opendilab/LightZero
puyuan1996 Jul 16, 2024
00f82fb
polish(pu): add unizero quick start in readme
puyuan1996 Jul 24, 2024
fff7fde
polish(pu): rename model_update_ratio to replay_ratio
puyuan1996 Jul 25, 2024
c004eac
Update requirements.txt
TuTuHuss Jul 30, 2024
f062baa
polish(pu): polish algo_overview
puyuan1996 Aug 1, 2024
4c68ac8
feature(xcy): add Metadrive Env and its SEZ configs (#192)
HarryXuancy Aug 2, 2024
5de52bc
feature(hus): add self-hosted linux(ubuntu) ci runner (#259)
TuTuHuss Aug 2, 2024
3f6cb5a
polish(nyz): add metadrive version info
PaParaZz1 Aug 3, 2024
0064381
fix(pu): fix DownSample for different obs shape (#254)
puyuan1996 Aug 15, 2024
8300a52
feature(pu): add Sampled MuZero/UniZero, DMC env and related configs …
puyuan1996 Aug 18, 2024
9e372fd
fix(pu): fix np.asarray in sampled related buffer/policy
puyuan1996 Aug 19, 2024
0040f46
feature(wrh): add continuous in mt
ruiheng123 Aug 26, 2024
ac238e9
feature(wrh): add continuous in mt
ruiheng123 Aug 26, 2024
9201454
feature(wrh): add continuous in mt
ruiheng123 Aug 26, 2024
0358781
Merge remote-tracking branch 'origin/main' into dev-unizero-multitask…
puyuan1996 Aug 28, 2024
5871aa6
feature(pu): add init version of multitask_sampled_unizero pipeline f…
puyuan1996 Aug 28, 2024
5f95d52
feature(wrh): initial debug for cont
ruiheng123 Aug 29, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 38 additions & 0 deletions .github/workflows/deploy.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
name: Deploy Sphinx Docs to GitHub Pages

on:
push:
branches:
- main

jobs:
build:
runs-on: ubuntu-latest

steps:
- name: Checkout the repository
uses: actions/checkout@v2

- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.11'

- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install --upgrade -r requirements-doc.txt
pip install -e .
pip install sphinx sphinx-rtd-theme recommonmark

- name: Build the Sphinx documentation
run: |
cd docs
make html
cp ../.nojekyll ./build/html/.nojekyll

- name: Deploy to GitHub Pages
uses: peaceiris/actions-gh-pages@v3
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
publish_dir: ./docs/build/html
16 changes: 9 additions & 7 deletions .github/workflows/test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ jobs:
fail-fast: false
matrix:
os:
- 'self-hosted-ubuntu'
- 'self-hosted'
- 'macos-12'
python-version:
- '3.8'
Expand All @@ -30,6 +30,8 @@ jobs:
if: ${{ runner.os == 'Linux' }}
shell: bash
run: |
sudo apt-get update -y
sudo apt-get install swig -y
echo "OS_NAME=Linux" >> $GITHUB_ENV
echo "IS_WIN=" >> $GITHUB_ENV
echo "IS_MAC=" >> $GITHUB_ENV
Expand Down Expand Up @@ -64,13 +66,13 @@ jobs:
shell: bash
run: |
python -m pip install --upgrade pip
pip install --upgrade flake8 setuptools wheel twine
pip install -r requirements.txt
pip install -r requirements-build.txt
pip install -r requirements-test.txt
pip install --no-cache-dir --upgrade flake8 setuptools wheel twine -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install -r requirements.txt --upgrade --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install -r requirements-build.txt --upgrade --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install -r requirements-test.txt --upgrade --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple
pip uninstall DI-engine -y
pip install git+http://github.com/opendilab/DI-engine.git@main#egg=DI-engine[common_env]
pip install transformers
pip install --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple git+http://github.com/opendilab/DI-engine.git@main#egg=DI-engine[common_env] --upgrade
pip install --no-cache-dir transformers --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
- name: Run unittest on MacOS or Linux
if: ${{ env.OS_NAME == 'MacOS' || env.OS_NAME == 'Linux'}}
env:
Expand Down
Empty file added .nojekyll
Empty file.
36 changes: 36 additions & 0 deletions .readthedocs.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
# Read the Docs configuration file for Sphinx projects
# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details

# Required
version: 2

# Set the OS, Python version and other tools you might need
build:
os: ubuntu-22.04
tools:
python: "3.9"
# You can also specify other tool versions:
# nodejs: "20"
# rust: "1.70"
# golang: "1.20"

# Build documentation in the "docs/" directory with Sphinx
sphinx:
configuration: docs/en/source/conf.py
# You can configure Sphinx to use a different builder, for instance use the dirhtml builder for simpler URLs
# builder: "dirhtml"
# Fail on all warnings to avoid broken references
# fail_on_warning: true

# Optionally build your docs in additional formats such as PDF and ePub
formats:
- pdf
- epub
- htmlzip

# Optional but recommended, declare the Python requirements required
# to build your documentation
# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
python:
install:
- requirements: requirements-doc.txt
9 changes: 9 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,12 @@
2024.07.12 (v0.1.0)
- env: SumToThree env from pooltool(#227)
- algo: UniZero (#232)
- algo: ReZero (#238)
- feature: add logs and config documentations (#220)
- polish: polish atari_env_action_space_map, fix test_muzero_game_buffer
- polish: polish release.yml
- style: update discord link and add a new badge in readme (#221)

2024.04.12 (v0.0.5)
- env: MemoryEnv (#197)
- env: mountain_car (#181)
Expand Down
107 changes: 62 additions & 45 deletions README.md

Large diffs are not rendered by default.

113 changes: 61 additions & 52 deletions README.zh.md

Large diffs are not rendered by default.

Binary file removed assets/algo_overview/efficientzero_overview.pdf
Binary file not shown.
Binary file removed assets/algo_overview/gumbel_muzero_overview.pdf
Binary file not shown.
Binary file removed assets/algo_overview/muzero_overview.pdf
Binary file not shown.
Binary file removed assets/algo_overview/sampled_muzero_overview.pdf
Binary file not shown.
11 changes: 11 additions & 0 deletions docs/.gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
*.puml.eps
*.puml.jpg
*.puml.svg
.DS_Store
../build/
source/_build
_build/
.vscode/
venv/
.idea/
src/pytorch-sphinx-theme/
71 changes: 22 additions & 49 deletions docs/Makefile
Original file line number Diff line number Diff line change
@@ -1,62 +1,35 @@
# You can set these variables from the command line, and also
# from the environment for the first two.
SPHINXOPTS ?=
SPHINXBUILD ?= $(shell which sphinx-build)
SPHINXMULTIVERSION ?= $(shell which sphinx-multiversion)
SOURCEDIR ?= source
BUILDDIR ?= build

# Minimal makefile for Sphinx documentation
DIAGRAMS_MK := ${SOURCEDIR}/diagrams.mk
DIAGRAMS := $(MAKE) -f "${DIAGRAMS_MK}" SOURCE=${SOURCEDIR}
GRAPHVIZ_MK := ${SOURCEDIR}/graphviz.mk
GRAPHVIZ := $(MAKE) -f "${GRAPHVIZ_MK}" SOURCE=${SOURCEDIR}
DEMOS_MK := ${SOURCEDIR}/demos.mk
DEMOS := $(MAKE) -f "${DEMOS_MK}" SOURCE=${SOURCEDIR}
NOTEBOOK_MK := ${SOURCEDIR}/notebook.mk
NOTEBOOK := $(MAKE) -f "${NOTEBOOK_MK}" SOURCE=${SOURCEDIR}

_CURRENT_PATH := ${PATH}
_PROJ_DIR := $(shell readlink -f ${CURDIR}/..)
_LIBS_DIR := $(shell readlink -f ${SOURCEDIR}/_libs)
_SHIMS_DIR := $(shell readlink -f ${SOURCEDIR}/_shims)
DIAGRAMS_MK := diagrams.mk
DIAGRAMS := $(MAKE) -f "${DIAGRAMS_MK}"

.EXPORT_ALL_VARIABLES:
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
SPHINXLIVE = sphinx-autobuild
SOURCEDIR = source
BUILDDIR = build

PYTHONPATH = ${_PROJ_DIR}:${_LIBS_DIR}
PATH = ${_SHIMS_DIR}:${_CURRENT_PATH}
NO_CONTENTS_BUILD = true

# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
# Put it first so that "make" without argument is like "make help".
.PHONY: help contents build html prod clean sourcedir builddir Makefile

help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

contents:
# Build & clean the documentation
diagrams:
@$(DIAGRAMS) build
@$(GRAPHVIZ) build
@$(DEMOS) build
@$(NOTEBOOK) build
build: html
html: contents
html: diagrams
@$(SPHINXBUILD) -M html "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
@touch "$(BUILDDIR)/html/.nojekyll"
prod:
@NO_CONTENTS_BUILD='' $(SPHINXMULTIVERSION) "$(SOURCEDIR)" "$(BUILDDIR)/html" $(SPHINXOPTS) $(O)
@cp main_page.html "$(BUILDDIR)/html/index.html"
@touch "$(BUILDDIR)/html/.nojekyll"

@$(SPHINXBUILD) -M html "$(SOURCEDIR)" "$(BUILDDIR)" ./source/**/*_zh.* $(SPHINXOPTS) $(O) -D master_doc=index_zh
live: diagrams
@$(SPHINXLIVE) "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
build: html
clean:
@$(DIAGRAMS) clean
@$(GRAPHVIZ) clean
@$(DEMOS) clean
@$(NOTEBOOK) clean
@$(SPHINXBUILD) -M clean "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

sourcedir:
@echo $(shell readlink -f ${SOURCEDIR})
builddir:
@echo $(shell readlink -f ${BUILDDIR}/html)
.PHONY: help diagrams html build clean Makefile

# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(DIAGRAMS) build
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
60 changes: 60 additions & 0 deletions docs/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
# 🎨 Welcome to LightZero Docs

[![Documentation Status](https://readthedocs.org/projects/lightzero-docs/badge/?version=latest)](https://lightzero-docs.readthedocs.io/en/latest/?badge=latest)

[LightZero](https://arxiv.org/pdf/2310.08348.pdf) is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL).

The LightZero documentation can be found [here](https://opendilab.github.io/LightZero/). It contains tutorials and the API reference.

For those interested in customizing environments and algorithms, we provide relevant guides:

- [Customize Environments](https://github.com/opendilab/LightZero/blob/main/docs/en/source//tutorials/envs/customize_envs.md)
- [Customize Algorithms](https://github.com/opendilab/LightZero/blob/main/docs/en/source//tutorials/algos/customize_algos.md)
- [How to Set Configuration Files?](https://github.com/opendilab/LightZero/blob/main/docs/en/source//tutorials/config/config.md)
- [Logging and Monitoring System](https://github.com/opendilab/LightZero/blob/main/docs/en/source//tutorials/logs/logs.md)

Should you have any questions, feel free to contact us for support.


# ⚙️ Local Docs Generation
```bash
# step 1: install
cd LightZero
pip install -r requirements-doc.txt
# step 2: compile docs
cd LightZero/docs/source
make live
# step 3: open http://127.0.0.1:8000 in your browser, and explore it!
```

# 🌏 Citing LightZero-docs

```latex
@article{niu2024lightzero,
title={LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios},
author={Niu, Yazhe and Pu, Yuan and Yang, Zhenjie and Li, Xueyan and Zhou, Tong and Ren, Jiyuan and Hu, Shuai and Li, Hongsheng and Liu, Yu},
journal={Advances in Neural Information Processing Systems},
volume={36},
year={2024}
}

@article{pu2024unizero,
title={UniZero: Generalized and Efficient Planning with Scalable Latent World Models},
author={Pu, Yuan and Niu, Yazhe and Ren, Jiyuan and Yang, Zhenjie and Li, Hongsheng and Liu, Yu},
journal={arXiv preprint arXiv:2406.10667},
year={2024}
}

@article{xuan2024rezero,
title={ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze},
author={Xuan, Chunyu and Niu, Yazhe and Pu, Yuan and Hu, Shuai and Liu, Yu and Yang, Jing},
journal={arXiv preprint arXiv:2404.16364},
year={2024}
}
```
# Contact Us
If you have any questions about documentation, please add a new issue or contact `[email protected]`

# License

LightZero-Docs released under the Apache 2.0 license
File renamed without changes.
9 changes: 0 additions & 9 deletions docs/main_page.html

This file was deleted.

35 changes: 35 additions & 0 deletions docs/make.bat
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
@ECHO OFF

pushd %~dp0

REM Command file for Sphinx documentation

if "%SPHINXBUILD%" == "" (
set SPHINXBUILD=sphinx-build
)
set SOURCEDIR=source
set BUILDDIR=build

if "%1" == "" goto help

%SPHINXBUILD% >NUL 2>NUL
if errorlevel 9009 (
echo.
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
echo.installed, then set the SPHINXBUILD environment variable to point
echo.to the full path of the 'sphinx-build' executable. Alternatively you
echo.may add the Sphinx directory to PATH.
echo.
echo.If you don't have Sphinx installed, grab it from
echo.http://sphinx-doc.org/
exit /b 1
)

%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
goto end

:help
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%

:end
popd
6 changes: 6 additions & 0 deletions docs/source/_static/css/style.css
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
.header-logo {
background-image: url("../../../../LightZero.png");
background-size: 180px 40px;
height: 40px;
width: 180px;
}
4 changes: 4 additions & 0 deletions docs/source/_templates/layout.html
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
{% extends "!layout.html" %}
{% block extrahead %}
<link href="{{ pathto("_static/css/style.css", True) }}" rel="stylesheet" type="text/css">
{% endblock %}
22 changes: 22 additions & 0 deletions docs/source/api_doc/agent/index.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
Agent
==========

.. autoclass:: lzero.agent.alphazero.AlphaZeroAgent
:members:

.. autoclass:: lzero.agent.muzero.MuZeroAgent
:members:

.. autoclass:: lzero.agent.efficientzero.EfficientZeroAgent
:members:

.. autoclass:: lzero.agent.gumbel_muzero.GumbelMuZeroAgent
:members:

.. autoclass:: lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent
:members:

.. autoclass:: lzero.agent.sampled_alphazero.SampledAlphaZeroAgent
:members:


6 changes: 3 additions & 3 deletions docs/source/api_doc/config/index.rst
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
lzero.config
Config
=====================

.. toctree::
:maxdepth: 3
:maxdepth: 2

meta
meta
Loading