Reinforcement Learning Ramp Metering without Complete Information | Zendy

Xing-Ju Wang | Zendy; Xiao-Ming Xi | Zendy; GuiFeng Gao | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Reinforcement Learning Ramp Metering without Complete Information

Author(s) -

Xing-Ju Wang,

Xiao-Ming Xi,

GuiFeng Gao

Publication year - 2012

Publication title -

journal of control science and engineering

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.208

H-Index - 18

eISSN - 1687-5257

pISSN - 1687-5249

DOI - 10.1155/2012/208456

Subject(s) - metering mode , reinforcement learning , reinforcement , inflow , automaticity , traffic flow (computer networking) , stability (learning theory) , computer science , process (computing) , control theory (sociology) , control (management) , outflow , simulation , engineering , artificial intelligence , machine learning , psychology , cognition , mechanics , structural engineering , geography , mechanical engineering , physics , computer security , neuroscience , meteorology , operating system

This paper develops a model of reinforcement learning ramp metering (RLRM) without complete information, which is applied to alleviate traffic congestions on ramps. RLRM consists of prediction tools depending on traffic flow simulation and optimal choice model based on reinforcement learning theories. Moreover, it is also a dynamic process with abilities of automaticity, memory and performance feedback. Numerical cases are given in this study to demonstrate RLRM such as calculating outflow rate, density, average speed, and travel time compared to no control and fixed-time control. Results indicate that the greater is the inflow, the more is the effect. In addition, the stability of RLRM is better than fixed-time control

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research