• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Calibration of agent-based model using reinforcement learning
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Calibration of agent-based model using reinforcement learning

Abstract
In the research and application of Agent-Based Models (ABM), parameter calibration is an important content. Based on the existing state transfer equations that link the micro-parameters and macro-states of the multi-agent system, this paper further proposes to introduce Reinforcement Learning when calibrating the parameters. The state transfer of the agent after learning is used to calibrate the micro-parameters of ABM, and the interaction between each agent and multiple other agents is expressed as the parameters of the agent. The application case study of population migration demonstrates that our method can achieve high accuracy and low computational complexity.
Author(s)
Song, Bing
Chinese Academy of Sciences, Institute of Automation, The State Key Laboratory for Management and Control of Complex Systems
Xiong, Gang
Chinese Academy of Sciences, Institute of Automation, The State Key Laboratory for Management and Control of Complex Systems
Yu, Songmin
Fraunhofer-Institut für System- und Innovationsforschung ISI
Ye, Peijun
Chinese Academy of Sciences, Institute of Automation, The State Key Laboratory for Management and Control of Complex Systems
Dong, Xisong
Chinese Academy of Sciences, Institute of Automation, The State Key Laboratory for Management and Control of Complex Systems
Lv, Yisheng
Chinese Academy of Sciences, Institute of Automation, The State Key Laboratory for Management and Control of Complex Systems
Hauptwerk
IEEE 1st International Conference on Digital Twins and Parallel Intelligence, DTPI 2021. Proceedings
Konferenz
International Conference on Digital Twins and Parallel Intelligence (DTPI) 2021
Thumbnail Image
DOI
10.1109/DTPI52967.2021.9540180
Language
English
google-scholar
Fraunhofer-Institut für System- und Innovationsforschung ISI
Tags
  • agent based model

  • reinforcement learnin...

  • calibration

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022