Cargando…

OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems

This paper presents an open-source, parallel AI environment (named OpenGraphGym) to facilitate the application of reinforcement learning (RL) algorithms to address combinatorial graph optimization problems. This environment incorporates a basic deep reinforcement learning method, and several graph e...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Weijian, Wang, Dali, Song, Fengguang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7302566/
http://dx.doi.org/10.1007/978-3-030-50426-7_33
_version_ 1783547873005142016
author Zheng, Weijian
Wang, Dali
Song, Fengguang
author_facet Zheng, Weijian
Wang, Dali
Song, Fengguang
author_sort Zheng, Weijian
collection PubMed
description This paper presents an open-source, parallel AI environment (named OpenGraphGym) to facilitate the application of reinforcement learning (RL) algorithms to address combinatorial graph optimization problems. This environment incorporates a basic deep reinforcement learning method, and several graph embeddings to capture graph features, it also allows users to rapidly plug in and test new RL algorithms and graph embeddings for graph optimization problems. This new open-source RL framework is targeted at achieving both high performance and high quality of the computed graph solutions. This RL framework forms the foundation of several ongoing research directions, including 1) benchmark works on different RL algorithms and embedding methods for classic graph problems; 2) advanced parallel strategies for extreme-scale graph computations, as well as 3) performance evaluation on real-world graph solutions.
format Online
Article
Text
id pubmed-7302566
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-73025662020-06-19 OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems Zheng, Weijian Wang, Dali Song, Fengguang Computational Science – ICCS 2020 Article This paper presents an open-source, parallel AI environment (named OpenGraphGym) to facilitate the application of reinforcement learning (RL) algorithms to address combinatorial graph optimization problems. This environment incorporates a basic deep reinforcement learning method, and several graph embeddings to capture graph features, it also allows users to rapidly plug in and test new RL algorithms and graph embeddings for graph optimization problems. This new open-source RL framework is targeted at achieving both high performance and high quality of the computed graph solutions. This RL framework forms the foundation of several ongoing research directions, including 1) benchmark works on different RL algorithms and embedding methods for classic graph problems; 2) advanced parallel strategies for extreme-scale graph computations, as well as 3) performance evaluation on real-world graph solutions. 2020-05-25 /pmc/articles/PMC7302566/ http://dx.doi.org/10.1007/978-3-030-50426-7_33 Text en © This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Zheng, Weijian
Wang, Dali
Song, Fengguang
OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title_full OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title_fullStr OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title_full_unstemmed OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title_short OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems
title_sort opengraphgym: a parallel reinforcement learning framework for graph optimization problems
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7302566/
http://dx.doi.org/10.1007/978-3-030-50426-7_33
work_keys_str_mv AT zhengweijian opengraphgymaparallelreinforcementlearningframeworkforgraphoptimizationproblems
AT wangdali opengraphgymaparallelreinforcementlearningframeworkforgraphoptimizationproblems
AT songfengguang opengraphgymaparallelreinforcementlearningframeworkforgraphoptimizationproblems