Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning
We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm a...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Publishing Corporation
2015
|
| Online Access: | http://hdl.handle.net/1721.1/96101 https://orcid.org/0000-0001-9618-1384 |
| _version_ | 1811092613822939136 |
|---|---|
| author | Yang, Min Yang, Yingxiang Wang, Wei Ding, Haoyang Chen, Jian |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Yang, Min Yang, Yingxiang Wang, Wei Ding, Haoyang Chen, Jian |
| author_sort | Yang, Min |
| collection | MIT |
| description | We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm as a medium that passes the influence of one traveler’s decision to others. Meanwhile, the agents used in the algorithm are initialized from typical activity patterns extracted from the travel survey diary data of Shangyu city in China. In the simulation, both macroscopic activity-travel characteristics such as traffic flow spatial-temporal distribution and microscopic characteristics such as activity-travel schedules of each agent are obtained. Comparing the simulation results with the survey data, we find that deviation of the peak-hour traffic flow is less than 5%, while the correlation of the simulated versus survey location choice distribution is over 0.9. |
| first_indexed | 2024-09-23T15:20:52Z |
| format | Article |
| id | mit-1721.1/96101 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:20:52Z |
| publishDate | 2015 |
| publisher | Hindawi Publishing Corporation |
| record_format | dspace |
| spelling | mit-1721.1/961012022-09-29T14:23:12Z Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning Yang, Min Yang, Yingxiang Wang, Wei Ding, Haoyang Chen, Jian Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Yang, Yingxiang We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm as a medium that passes the influence of one traveler’s decision to others. Meanwhile, the agents used in the algorithm are initialized from typical activity patterns extracted from the travel survey diary data of Shangyu city in China. In the simulation, both macroscopic activity-travel characteristics such as traffic flow spatial-temporal distribution and microscopic characteristics such as activity-travel schedules of each agent are obtained. Comparing the simulation results with the survey data, we find that deviation of the peak-hour traffic flow is less than 5%, while the correlation of the simulated versus survey location choice distribution is over 0.9. National Basic Research Program of China (973 Program) (2012CB725400) National Natural Science Foundation (China) (51378120) National Natural Science Foundation (China) (51338003) 2015-03-20T13:21:49Z 2015-03-20T13:21:49Z 2014-01 2013-11 2015-03-19T11:33:37Z Article http://purl.org/eprint/type/JournalArticle 1024-123X 1563-5147 http://hdl.handle.net/1721.1/96101 Yang, Min, Yingxiang Yang, Wei Wang, Haoyang Ding, and Jian Chen. “Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning.” Mathematical Problems in Engineering 2014 (2014): 1–11. https://orcid.org/0000-0001-9618-1384 en http://dx.doi.org/10.1155/2014/951367 Mathematical Problems in Engineering Creative Commons Attribution http://creativecommons.org/licenses/by/2.0 Copyright © 2014 Min Yang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. application/pdf Hindawi Publishing Corporation Hindawi Publishing Corporation |
| spellingShingle | Yang, Min Yang, Yingxiang Wang, Wei Ding, Haoyang Chen, Jian Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title | Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title_full | Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title_fullStr | Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title_full_unstemmed | Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title_short | Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning |
| title_sort | multiagent based simulation of temporal spatial characteristics of activity travel patterns using interactive reinforcement learning |
| url | http://hdl.handle.net/1721.1/96101 https://orcid.org/0000-0001-9618-1384 |
| work_keys_str_mv | AT yangmin multiagentbasedsimulationoftemporalspatialcharacteristicsofactivitytravelpatternsusinginteractivereinforcementlearning AT yangyingxiang multiagentbasedsimulationoftemporalspatialcharacteristicsofactivitytravelpatternsusinginteractivereinforcementlearning AT wangwei multiagentbasedsimulationoftemporalspatialcharacteristicsofactivitytravelpatternsusinginteractivereinforcementlearning AT dinghaoyang multiagentbasedsimulationoftemporalspatialcharacteristicsofactivitytravelpatternsusinginteractivereinforcementlearning AT chenjian multiagentbasedsimulationoftemporalspatialcharacteristicsofactivitytravelpatternsusinginteractivereinforcementlearning |