Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers
Abstract
We present Ecole, a new library to simplify machine learning research for combinatorial optimization. Ecole exposes several key decision tasks arising in general-purpose combinatorial optimization solvers as control problems over Markov decision processes. Its interface mimics the popular OpenAI Gym library and is both extensible and intuitive to use. We aim at making this library a standardized platform that will lower the bar of entry and accelerate innovation in this growing field. Documentation and code can be found at https://www.ecole.ai.
Cite
Text
Prouvost et al. "Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers." NeurIPS 2020 Workshops: LMCA, 2020.Markdown
[Prouvost et al. "Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers." NeurIPS 2020 Workshops: LMCA, 2020.](https://mlanthology.org/neuripsw/2020/prouvost2020neuripsw-ecole/)BibTeX
@inproceedings{prouvost2020neuripsw-ecole,
title = {{Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers}},
author = {Prouvost, Antoine and Dumouchelle, Justin and Scavuzzo, Lara and Gasse, Maxime and Chételat, Didier and Lodi, Andrea},
booktitle = {NeurIPS 2020 Workshops: LMCA},
year = {2020},
url = {https://mlanthology.org/neuripsw/2020/prouvost2020neuripsw-ecole/}
}