arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.04434cs.LG
收藏

开发OpenAI Gym-compatible框架和模拟环境,用于测试深度强化学习代理解决救护车定位问题

Developing an OpenAI Gym-compatible framework and simulation environment for testing Deep Reinforcement Learning agents solving the Ambulance Location Problem

University of Exeter(埃克塞特大学);University of Exeter Medical School(埃克塞特大学医学院)

Michael Allen, Kerry Pearn, Tom Monks

摘要:

背景和动机:深度强化学习(Deep RL)是一个快速发展的领域。历史上,大多数应用程序都是用于游戏(如国际象棋,Atari游戏和围棋)。深度RL现在已经达到了可以为现实世界的问题提供价值的阶段,包括优化医疗保健系统。其中一个问题是在呼叫之间定位救护车,以最大限度地减少从紧急呼叫到救护车到达现场的时间。这就是所谓的救护车定位问题。目的:开发OpenAI Gym-compatible框架和模拟环境,用于测试Deep RL代理。方法:使用OpenAI Gym和SimPy开发自定义救护车调度仿真环境。深度RL代理是使用PyTorch构建的。该环境是现实世界的简化,但允许控制事件位置的集群数量、可能的调度位置的数量、医院的数量,并创建每天在不同位置发生的事件。结果:在此自定义环境中测试了一系列基于Deep Q网络的Deep RL代理。与随机分配到调度点相比,所有这些都缩短了响应紧急呼叫的时间。Bagging Noisy Duelling Deep Q网络提供了最一致的性能。如果训练时间过长,所有方法都有失去性能的倾向,因此代理都以其最佳性能保存(并在独立的模拟运行中进行测试)。结论:使用模拟环境开发的深度RL代理有可能提供一种新的方法来优化救护车定位问题。创建开放的模拟环境应该可以在这一领域取得更快的进展。

英文摘要:

Background and motivation: Deep Reinforcement Learning (Deep RL) is a rapidly developing field. Historically most application has been made to games (such as chess, Atari games, and go). Deep RL is now reaching the stage where it may offer value in real world problems, including optimisation of healthcare systems. One such 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. Aim: To develop an OpenAI Gym-compatible framework and simulation environment for testing Deep RL agents. Methods: A custom ambulance dispatch simulation environment was developed using OpenAI Gym and SimPy. Deep RL agents were built using PyTorch. The environment is a simplification of the real world, but allows control over the number of clusters of incident locations, number of possible dispatch locations, number of hospitals, and creating incidents that occur at different locations throughout each day. Results: A range of Deep RL agents based on Deep Q networks were tested in this custom environment. All reduced time to respond to emergency calls compared with random allocation to dispatch points. Bagging Noisy Duelling Deep Q networks gave the most consistence performance. All methods had a tendency to lose performance if trained for too long, and so agents were saved at their optimal performance (and tested on independent simulation runs). Conclusions: Deep RL agents, developed using simulated environments, have the potential to offer a novel approach to optimise the Ambulance Location problem. Creating open simulation environments should allow more rapid progress in this field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑