Alleviating Community Fear in Disasters via Multi-Agent Actor-Critic Reinforcement Learning
2026-04-09 • Machine Learning
Machine Learning
AI summaryⓘ
The authors extend a model that looks at how disasters cause problems in power, communication, and people's behaviors to spread fear and disrupt help efforts. They add ways for three agencies—communication, power, and emergency management—to actively intervene during a disaster. Using a type of machine learning, they simulate these efforts with real hurricane data and show that their approach can significantly reduce fear and help fix infrastructure faster. Testing with a different hurricane's data also showed good results, suggesting the model works well beyond one example.
cyber-physical-social systemscascading failuresdifferential gamesactor-critic reinforcement learninginfrastructure recoveryHurricane HarveyHurricane Irmafear reductionmulti-agent controldisaster resilience
Authors
Yashodhan D. Hakke, Almuatazbellah M. Boker, Lamine Mili, Michael von Spakovsky, Hoda Eldardiry
Abstract
During disasters, cascading failures across power grids, communication networks, and social behavior amplify community fear and undermine cooperation. Existing cyber-physical-social (CPS) models simulate these coupled dynamics but lack mechanisms for active intervention. We extend the CPS resilience model of Valinejad and Mili (2023) with control channels for three agencies, communication, power, and emergency management, and formulate the resulting system as a three-player non-zero-sum differential game solved via online actor-critic reinforcement learning. Simulations based on Hurricane Harvey data show 70% mean fear reduction with improved infrastructure recovery; cross-validation in the case of Hurricane Irma (without refitting) achieves 50% fear reduction, confirming generalizability.