Police patrol path planning using Stackelberg equilibrium based multiagent reinforcement learning

DOI10.15918/J.TBIT1001-0645.2017.01.019MaRDI QIDQ5371883zbMATH OpenFDO

Authors Yi Xie, Yijun Gu

Publication date 20 October 2017

Full work available at URL https://doi.org/10.15918/J.TBIT1001-0645.2017.01.019

zbMATH Keywords

multiagentpatrol path planningreinforcement learningstrong Stackelberg equilibrium

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Agent technology and artificial intelligence (68T42) Programming involving graphs or networks (90C35) Cooperative games (91A12)

Recommendations

• Adapting attackers and defenders patrolling strategies: a reinforcement learning approach for Stackelberg security games
• A continuous-time Markov Stackelberg security game approach for reasoning about real patrol strategies
• Handling a Kullback--Leibler divergence random walk for scheduling effective patrol strategies in Stackelberg security games
• A Monte Carlo tree search approach to finding efficient patrolling schemes on graphs
• On dynamic patrolling security games

Cited in

(2)

• Adapting attackers and defenders patrolling strategies: a reinforcement learning approach for Stackelberg security games
• Optimal patrolling path planning via linear temporal logic

This page was built for publication: Police patrol path planning using Stackelberg equilibrium based multiagent reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5371883)