Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning
Conference Paper
-
- Overview
-
- Identity
-
- Additional Document Info
-
- Other
-
- View All
-
Overview
abstract
-
© 2018 IEEE. In the micro-tolling paradigm, a centralized system manager sets different toll values for each link in a given traffic network with the objective of optimizing the system's performance. A recently proposed micro-tolling scheme, denoted Delta-tolling, was shown to yield up to 32% reduction in total travel time when compared to a no-toll scheme. Delta-tolling, computes a toll value for each link in a given network based on two global parameters: \beta which is a proportional parameter and R which controls the rate of toll change over time. In this paper, we propose to generalize Delta-tolling such that it would consider different R and \beta parameters for each link. a policy gradient reinforcement learning algorithm is used in order to tune this high-dimensional optimization problem. The results show that such a variant of Delta-tolling far surpasses the original Delta-tolling scheme, yielding up to 38% reduced system travel time compared to the original Delta-tolling scheme.
name of conference
-
2018 21st International Conference on Intelligent Transportation Systems (ITSC)
published proceedings
-
2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
author list (cited authors)
-
Mirzaei, H., Sharon, G., Boyles, S., Givargis, T., & Stone, P.
citation count
complete list of authors
-
Mirzaei, Hamid||Sharon, Guni||Boyles, Stephen||Givargis, Tony||Stone, Peter
publication date
publisher
published in
Identity
Digital Object Identifier (DOI)
International Standard Book Number (ISBN) 13
Additional Document Info
start page
end page
volume
Other
URL
-
http://dx.doi.org/10.1109/itsc.2018.8569737