Accelerating route choice learning with experience sharing in a commuting scenario: An agent-based approach

Author:

Klügl Franziska1,Bazzan Ana Lucia C.2

Affiliation:

1. School of Science and Technology, Örebro University, Sweden. E-mail: franziska.klugl@oru.se

2. Instituto de Informatica, Universidade Federal do Rio Grando do Sul (UFRGS), Brazil. E-mail: bazzan@inf.ufrgs.br

Abstract

Navigation apps have become more and more popular, as they give information about the current traffic state to drivers who then adapt their route choice. In commuting scenarios, where people repeatedly travel between a particular origin and destination, people tend to learn and adapt to different situations. What if the experience gained from such a learning task is shared via an app? In this paper, we analyse the effects that adaptive driver agents cause on the overall network, when those agents share their aggregated experience about route choice in a reinforcement learning setup. In particular, in this investigation, Q-learning is used and drivers share what they have learnt about the system, not just information about their current travel times. Using a classical commuting scenario, we show that experience sharing can improve convergence times that underlie a typical learning task. Further, we analyse individual learning dynamics to get an impression how aggregate and individual dynamics are related to each other. Based on that interesting pattern of individual learning dynamics can be observed that would otherwise be hidden in an only aggregate analysis.

Publisher

IOS Press

Subject

Artificial Intelligence

Reference37 articles.

1. Aligning individual and collective welfare in complex socio-technical systems by combining metaheuristics and reinforcement learning;Bazzan;Eng. Appl. of AI,2019

2. A.L.C. Bazzan and C. Chira, Hybrid evolutionary and reinforcement learning approach to accelerate traffic assignment (extended abstract), in: Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2015), R. Bordini, E. Elkind, G. Weiss and P. Yolum, eds, IFAAMAS, 2015, pp. 1723–1724, http://www.aamas2015.com/en/AAMAS_2015_USB/aamas/p1723.pdf.

3. A.L.C. Bazzan, M. Fehler and F. Klügl, Learning to coordinate in a network of social drivers: The role of information, in: Proceedings of the International Workshop on Learning and Adaptation in MAS (LAMAS 2005), K. Tuyls, P.J. Hoen, K. Verbeeck and S. Sen, eds, Lecture Notes in Artificial Intelligence, 2006, pp. 115–128, www.inf.ufrgs.br/~bazzan/downloads/lamas38980115.pdf.gz.

4. A multiagent reinforcement learning approach to en-route trip building

5. A.L.C. Bazzan and F. Klügl, Experience sharing in a traffic scenario, in: Proc. of the 11th Int. Workshop on Agents in Traffic and Transportation, Santiago de Compostella, Spain, 4 Sept. 2020, 2020.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3