Targets in Reinforcement Learning to solve Stackelberg Security Games

Authors: Saptarashmi Bandyopadhyay, Chenqi Zhu, Philip Daniel, Joshua Morrison, Ethan Shay, John Dickerson
Published: 2022-11-30

Source: https://arxiv.org/abs/2211.17132

PDF: https://arxiv.org/pdf/2211.17132

AIにより推定されたラベル

スタッキングモデル セキュリティ保証 アルゴリズム設計

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Reinforcement Learning (RL) algorithms have been successfully applied to real world situations like illegal smuggling, poaching, deforestation, climate change, airport security, etc. These scenarios can be framed as Stackelberg security games (SSGs) where defenders and attackers compete to control target resources. The algorithm’s competency is assessed by which agent is controlling the targets. This review investigates modeling of SSGs in RL with a focus on possible improvements of target representations in RL algorithms.