On Improving the Properties of Random Walk on Graph using Q-learning

Ryotaro Matsuo; Tomoyuki Miyashita; Taisei Suzuki; Hiroyuki Ohsaki

doi:10.1587/comex.2022XBL0153

この記事には本公開記事があります。本公開記事を参照してください。
引用する場合も本公開記事を引用してください。

On Improving the Properties of Random Walk on Graph using Q-learning

Ryotaro Matsuo, Tomoyuki Miyashita, Taisei Suzuki, Hiroyuki Ohsaki

著者情報

キーワード: Random walk, Q-weighted random walk, Q-learning, reinforcement learning, mobility model

ジャーナルフリー早期公開

論文ID: 2022XBL0153

DOI https://doi.org/10.1587/comex.2022XBL0153

この記事には本公開記事があります。

The final version of this article is now available: Vol. 12 (2023), No. 1 pp. 36-41

詳細

抄録

Studies have recently been conducted to model mobile agents on unknown graphs, such as random walks (RWs) on graphs, and to understand their mathematical properties. In this study, we investigate the extent to which the properties of RWs can be improved when mobile agents have access to very limited information. We propose Q-weighted random walk (QW-RW), in which an agent decides a next node by using Q-values learned by Q-learning, and examine its effectiveness. We find that in small scale-free graphs, QW-RW is 1.25 times faster than self-avoiding RW to cover 80% of the entire graph.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）