# GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events

arXiv: https://arxiv.org/abs/2609.16163 · HTML: https://mlsanity.com/paper/2609.16163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification](https://mlsanity.com/paper/2302.11813/) (2023)
- [Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1906.04737/) (2019)
- [Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case](https://mlsanity.com/paper/1910.07421/) (2019)
- [Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training](https://mlsanity.com/paper/2107.14316/) (2021)
- [Leveraging Graph Neural Networks and Multi-Agent Reinforcement Learning for Inventory Control in Supply Chains](https://mlsanity.com/paper/2410.18631/) (2024)
- [Graph Attention Network-based Multi-agent Reinforcement Learning for Slicing Resource Management in Dense Cellular Network](https://mlsanity.com/paper/2108.05063/) (2021)
- [Simulating multi-exit evacuation using deep reinforcement learning](https://mlsanity.com/paper/2007.05783/) (2020)
- [Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles](https://mlsanity.com/paper/2012.00065/) (2020)
- [Active shooter detection and robust tracking utilizing supplemental synthetic data](https://mlsanity.com/paper/2309.03381/) (2023)
- [Graph Neural Networks for Travel Distance Estimation and Route Recommendation Under Probabilistic Hazards](https://mlsanity.com/paper/2501.09803/) (2025)
- [An Optimized Evacuation Plan for an Active-Shooter Situation Constrained by Network Capacity](https://mlsanity.com/paper/2505.07830/) (2025)

## Abstract (arXiv)

The sharp increase in mass shootings underscores an urgent need for systems that guide victims to safety in real time. An effective evacuation system must minimize threat exposure while also accounting for adversarial uncertainty and crowding dynamics. Current methods in the literature are rigidly constrained to layout-specific policies and computationally intractable in large-scale layouts, while practical guidelines simply advise victims to "run", "hide", or "fight". We propose GPEvac: a GNN-based PPO framework that computes adaptive evacuation routes during shooting events. To capture both local and long-distance dependencies, we introduce an edge-first sequential message-passing scheme with a learnable virtual global node. The resulting graph embeddings are integrated into a permutation-invariant scoring mechanism that allows a single learned policy to operate across building layouts of diverse topologies and sizes. Through extensive simulation, we show that GPEvac outperforms intelligent baselines across distinct architectural layouts, significantly reducing total threat exposure. Crucially, the system computes global evacuation routes in just 14.73 ms on local CPU hardware, enabling seamless integration with live surveillance systems. In addition to saving lives during shooting events, the methodologies developed are transferable to other graph-structured decision-making domains, including critical infrastructure, intelligent transportation systems, and adaptive sensor networks.