search

hubbs5 / or-gym

Environments for OR and RL Research
MIT License
373 stars 93 forks source link
deep-reinforcement-learning operations-research optimization reinforcement-learning supply-chain supply-chain-management vehicle-routing-problem

readme

or-gym

Environments for OR and RL Research

This library contains environments consisting of operations research problems which adhere to the OpenAI Gym API. The purpose is to bring reinforcement learning to the operations research community via accessible simulation environments featuring classic problems that are solved both with reinforcement learning as well as traditional OR techniques.

Installation

This library requires Python 3.5+ in order to function.

Installation is possible via pip:

$ pip install or-gym

Or, you can install directly from GitHub with:

git clone https://github.com/hubbs5/or-gym.git
cd or-gym
pip install -e .

Quickstart Example and Benchmarking Example

See the IPython notebook entitled inv-management-quickstart.ipynb in the examples folder for a quickstart example for training an agent in an OR-GYM environemnt, and for using the environment for benchmarking policies found by other algorithms. For the RL algorithm, Ray 1.0.0 is required.

Citation

@misc{HubbsOR-Gym,
    author={Christian D. Hubbs and Hector D. Perez and Owais Sarwar and Nikolaos V. Sahinidis and Ignacio E. Grossmann and John M. Wassick},
    title={OR-Gym: A Reinforcement Learning Library for Operations Research Problems},
    year={2020},
    Eprint={arXiv:2008.06319}
}

Environments

Resources

Information on results and supporting models can be found here.

Examples