We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edges. We demonstrate that this method is capable of generating DAGs with topology and node types satisfying specified criteria in highly sparse reward environments.
@article{arxiv.1906.02280,
title = {Deep Q-Learning for Directed Acyclic Graph Generation},
author = {Laura D'Arcy and Padraig Corcoran and Alun Preece},
journal= {arXiv preprint arXiv:1906.02280},
year = {2019}
}
Comments
Accepted to Learning and Reasoning with Graph-Structured Representations, ICML 2019 Workshop