PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 19, 2025Advanced Intelligent SystemsOpen Access

Learning Optimal Crowd Evacuation from Scratch Through Self‐Play

View Full Paper
Ask AI
Bookmark
Share

Authors

MNMahdi NasiriMCMalte CordtsHKHeinz Koeppl

Discussion

Loading...

Member takes

Overview

This study develops a method that improves crowd evacuation rates using reinforcement learning, suggesting better strategies for safety.

Key Points

  • Agents learn optimal crowd behavior autonomously, enhancing evacuation strategies based on pressure awareness.
  • The method demonstrated improved evacuation rates and lower fatalities compared to traditional models, indicating its effectiveness.
  • Using multiagent reinforcement learning, agents adopt interpretable strategies like queuing and zipper merging for efficient evacuation.
  • Potential applications of this work could lead to better safety guidelines for mass evacuations in various environments.

Cite This Study

Nasiri et al. (2025) studied this question.

synapsesocial.com/papers/68d464ea31b076d99fa64196https://doi.org/10.1002/aisy.202500436
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Crowd evacuation simulation based on hierarchical agent model and physics‐based character control2024 · 1 citations
  2. 2Agent-Based Simulation of Crowd Evacuation Through Complex Spaces2024 · 1 citations
  3. 3Crowd Evacuation Simulation Based on Hierarchical Agent Model and Physics-based Character Control2024
  4. 4Robot-Assisted Emergency Evacuation of Crowds: A Comprehensive Survey of Modeling Approaches, Intelligent Guidance Systems, and Future Research Directions2026
  5. 5A double‐layer crowd evacuation simulation method based on deep reinforcement learning2024 · 6 citations