This is a TensorFlow implementation of the deep reinforcement learning-enabled dynamic ambulance redeployment method proposed by paper "A Deep Reinforcement Learning-Enabled Dynamic Redeployment System for Mobile Ambulances" [1].

TensorFlow >= 1.5.0
numpy and scipy.

implements the training and evaluation of the deep reinforcement learning method
training or evaluation: python policy_n4.py

implements a simplified simulation

defines the network structure of the deep (neural) score network

contains some functions for data processing

[1] Shenggong Ji, Yu Zheng, Zhaoyuan Wang, Tianrui Li. A Deep Reinforcement Learning-Enabled Dynamic Redeployment System for Mobile Ambulances. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/UbiComp 2019) 3, 1, Article 15, 2019.