A classic Health Operations problem is where to locate ambulances between calls in order to minimise time from emergency call to ambulance on-scene. This is known as the Ambulance Location problem.
We have developed a simple simulation of this problem and have tested a range of deep reinforcement learning agents.
The paper describing the results is:
Allen M, Pearn K, Monks T. (2021) Developing an OpenAI Gym-compatible framework and simulation environment for testing Deep Reinforcement Learning agents solving the Ambulance Location Problem. arXiv:210104434 http://arxiv.org/abs/2101.04434
The GitHub repository for all the experiments is: https://github.com/MichaelAllen1966/qambo