Solving Maximal Stable Set Problem via Deep Reinforcement Learning

Taiyi Wang, Jiahao Shi

2021

Abstract

This paper provides an innovative method to approximate the optimal solution to the maximal stable set problem, a typical NP-hard combinatorial optimization problem. Different from traditional greedy or heuristic algorithms, we combine graph embedding and DQN-based reinforcement learning to make this NP-hard optimization problem trainable so that the optimal solution over new graphs can be approximated. This appears to be a new approach in solving maximal stable set problem. The learned policy is to choose a sequence of nodes incrementally to construct the stable set, with action determined by the outputs of graph embedding network over current partial solution. Our numerical experiments suggest that the proposed algorithm is promising in tackling the maximum stable independent set problem.

Paper Citation

in Harvard Style

Wang T. and Shi J. (2021). Solving Maximal Stable Set Problem via Deep Reinforcement Learning.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 483-489. DOI: 10.5220/0010179904830489

in Bibtex Style

@conference{icaart21,
author={Taiyi Wang and Jiahao Shi},
title={Solving Maximal Stable Set Problem via Deep Reinforcement Learning},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={483-489},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010179904830489},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Solving Maximal Stable Set Problem via Deep Reinforcement Learning
SN - 978-989-758-484-8
AU - Wang T.
AU - Shi J.
PY - 2021
SP - 483
EP - 489
DO - 10.5220/0010179904830489