Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
Перейти к файлу
Zhanyu Wang (Pactera) d80aaf36df fix q_curve chart order 2020-01-02 16:57:51 +08:00
docker_files remove dist dokcer file 2020-01-02 16:19:54 +08:00
docs init 2020-01-02 15:04:20 +08:00
examples fix q_curve chart order 2020-01-02 16:57:51 +08:00
maro fix q_curve chart order 2020-01-02 16:57:51 +08:00
notebooks init 2020-01-02 15:04:20 +08:00
tools remove unused scripts 2020-01-02 16:19:02 +08:00
.dockerignore init 2020-01-02 15:04:20 +08:00
.gitignore init 2020-01-02 15:04:20 +08:00
CODE_OF_CONDUCT.md Initial CODE_OF_CONDUCT.md commit 2019-12-26 22:48:32 -08:00
LICENSE Initial LICENSE commit 2019-12-26 22:48:34 -08:00
MANIFEST.in init 2020-01-02 15:04:20 +08:00
README.md init 2020-01-02 15:04:20 +08:00
SECURITY.md Initial SECURITY.md commit 2019-12-26 22:48:34 -08:00
build_manylinux.sh init 2020-01-02 15:04:20 +08:00
build_maro.bat add script to build maro for windows 2020-01-02 16:30:10 +08:00
build_maro.sh init 2020-01-02 15:04:20 +08:00
build_sdist.sh init 2020-01-02 15:04:20 +08:00
build_wheel.bat fix q_curve chart order 2020-01-02 16:57:51 +08:00
build_wheel.sh init 2020-01-02 15:04:20 +08:00
requirements.dev.txt init 2020-01-02 15:04:20 +08:00
setup.py init 2020-01-02 15:04:20 +08:00

README.md

MARO LOGO MARO(Multi-Agent Resource Optimization) is a multi-agent resource optimization platform, which is an end-to-end solution for both academic research and industry application. A super-fast and highly extensible simulator system and a scalable distributed system are provided, which can well support both small scale single host exploration and large scale distributed application. Some out-of-box scenarios, algorithms and related baselines are provided for a quick hands-on exploration.

Contents

File/folder Description
maro MARO source code.
examples Showcase of MARO.
tools Gulp-based helper scripts.
notebooks MARO quick-start notebooks.

Run from Source Code

Rerequisites

Build MARO

pip install -r requirements.dev.txt
export PYTHONPATH=$PWD:$PYTHONPATH
bash build_maro.sh

Run Examples

cd examples/ecr/q_learning/single_host_mode
bash silent_run.sh

Run in Docker (only support linux currently)

Refer to prerequisites for details.

cd tools
gulp l/build_image
gulp l/launch_container
gulp l/login_container
cd examples/ecr/q_learning/single_host_mode
bash silent_run.sh

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Reference Papers (TODO)

License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT License.