TY - GEN
T1 - Link-based parameterized micro-tolling scheme for optimal traffic management
AU - Mirzaei, Hamid
AU - Sharon, Guni
AU - Boyles, Stephen
AU - Givargis, Tony
AU - Stone, Peter
N1 - Publisher Copyright:
© 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - In the micro-tolling paradigm, different toll values are assigned to different links within a congestible traffic network. Self-interested agents then select minimal cost routes, where cost is a function of the travel time and tolls paid. A centralized system manager sets toll values with the objective of inducing a user equilibrium that maximizes the total utility over all agents. A recently proposed algorithm for computing such tolls, denoted A-tolling, was shown to yield up to 32% reduction in total travel time in simulated traffic scenarios compared to when there are no tolls. Δ-tolling includes two global parameters: β which is a proportionality parameter, and R which influences the rate of change of toll values across all links. This paper introduces a generalization of Δ-tolling which accounts for different β and R values on each link in the network. While this enhanced Δ-tolling algorithm requires setting significantly more parameters, we show that they can be tuned effectively via policy gradient reinforcement learning. Experimental results from several traffic scenarios indicate that Enhanced Δ-tolling reduces total travel time by up to 28% compared to the original Δ-tolling algorithm, and by up to 45% compared to not tolling.
AB - In the micro-tolling paradigm, different toll values are assigned to different links within a congestible traffic network. Self-interested agents then select minimal cost routes, where cost is a function of the travel time and tolls paid. A centralized system manager sets toll values with the objective of inducing a user equilibrium that maximizes the total utility over all agents. A recently proposed algorithm for computing such tolls, denoted A-tolling, was shown to yield up to 32% reduction in total travel time in simulated traffic scenarios compared to when there are no tolls. Δ-tolling includes two global parameters: β which is a proportionality parameter, and R which influences the rate of change of toll values across all links. This paper introduces a generalization of Δ-tolling which accounts for different β and R values on each link in the network. While this enhanced Δ-tolling algorithm requires setting significantly more parameters, we show that they can be tuned effectively via policy gradient reinforcement learning. Experimental results from several traffic scenarios indicate that Enhanced Δ-tolling reduces total travel time by up to 28% compared to the original Δ-tolling algorithm, and by up to 45% compared to not tolling.
KW - Micro-tolling
KW - Policy gradient
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85054718931&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85054718931
SN - 9781510868083
T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
SP - 2013
EP - 2015
BT - 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
T2 - 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
Y2 - 10 July 2018 through 15 July 2018
ER -