# Targets in Reinforcement Learning to solve Stackelberg Security Games

arXiv: https://arxiv.org/abs/2211.17132 · HTML: https://mlsanity.com/paper/2211.17132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 8 of 8)

- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [PettingZoo: Gym for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2009.14471/) (2020)
- [Evaluating the Robustness of Collaborative Agents](https://mlsanity.com/paper/2101.05507/) (2021)
- [Deep Reinforcement Learning for Green Security Games with Real-Time Information](https://mlsanity.com/paper/1811.02483/) (2018)
- [Model-free Reinforcement Learning for Stochastic Stackelberg Security Games](https://mlsanity.com/paper/2005.11853/) (2020)
- [Single-Leader-Multiple-Followers Stackelberg Security Game with Hypergame Framework](https://mlsanity.com/paper/2107.14625/) (2021)
- [On the Inducibility of Stackelberg Equilibrium for Security Games](https://mlsanity.com/paper/1811.03823/) (2018)
- [Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty](https://mlsanity.com/paper/2012.10389/) (2020)

## Abstract (arXiv)

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.