Determination and optimization of reinforcement learning parameters for driver actions in traffic

An agent-based, artificial intelligence technique known as reinforcement learning has been used to capture vehicle behavior and simulate driver's actions in traffic, especially during emergency situations. This paper discusses the training parameters and their influence on agent simulation performance. A type of agent training technique called Neuro-Fuzzy Actor Critic Reinforcement Learning (NFACRL) is used to test the training parameters with an objective of improving simulation performance. A systematic parameter determination and optimization methodology is provided.

• Record URL:
  https://doi.org/10.1109/ITSC.2011.6083090
• Availability:
  • Find a library where document is available. Order URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6069628
• Supplemental Notes:
  • Abstract reprinted with permission of IEEE.
• Corporate Authors:

  Institute of Electrical and Electronics Engineers (IEEE)

  3 Park Avenue, 17th Floor
  New York, NY  United States  10016-5997
• Authors:
  • Chong, Linsen
  • Abbas, M
  • Higgs, B
  • Medina, A
  • Yang, C Y D
• Conference:
  • 14th International IEEE Conference on Intelligent Transportation Systems (ITSC 2011)
  • Location: Washington DC, United States
  • Date: 2011-10-5 to 2011-10-7
• Publication Date: 2011-10

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 1785-1790
• Monograph Title: 14th International IEEE Conference on Intelligent Transportation Systems (ITSC 2011)

Subject/Index Terms

• TRT Terms: Behavior; Drivers; Intelligent agents; Machine learning; Optimization; Simulation; Vehicle dynamics
• Subject Areas: Highways; Planning and Forecasting; Safety and Human Factors; I70: Traffic and Transport;

Filing Info

• Accession Number: 01567429
• Record Type: Publication
• ISBN: 9781457721984
• Files: TRIS
• Created Date: May 20 2015 2:34PM