期刊论文、会议论文

Lu, Shoufeng

英文

Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

2008

2854-2858

7th World Congress on Intelligent Control and Automation

JUN 25-27, 2008

Chongqing, PEOPLES R CHINA

[Lu, Shoufeng;Liu, Ximin] Changsha Univ Sci & Technol, Traff & Transportat Coll, Changsha 410076, Hunan, Peoples R China.^[Liu, Ximin;Dai, Shiqiang] Shanghai Univ, Inst Appl Math & Mech, Shanghai 200072, Peoples R China.

Chongqing Univ, Chongqing Inst Technol, Chongqing Univ Sci & Technol, Xihua Univ, SW Univ Sci & Technol, IEEE Robot & Automat Soc, IEEE Control Syst Soc, Beijing Chapter, Chinese Assoc Automat, Chinese Assoc Artificial Intelligence, Natl Nat Sci Fdn, Chongqing Municipal Sci & Technol Comm, Chongqing Municipal Assoc Sci & Technol, KC Wong Educ Fdn

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-4244-2113-8

10.1109/WCICA.2008.4593378

NSFC [70701006, 10532060]; National Basic Research Program of China [2006CB705500]; Talent Recruitment Foundation of Changsha University of Science and Technology [1004140]

本校为第一且通讯机构

Incremental multistep Q learning (Q( λ)) combines Q learning and TD(λ). Theoretically, Q(λ) has better performance than Q learning. The goal of the paper is to test the performance of Q(λ) for adaptive traffic signal control. For Q(λ), the state is total delay of the intersection, and the action is phase green time change. The relationship between phase green time change and action space is discussed. The performance between Q(λ) learning and fixed cycle signal setting for isolated intersection is compared. The computation results show that Q(λ)...