Podium Session 6: Markov Game for CV Joint Adaptive Routing in Stochastic Traffic Networks: A Scalable Learning Approach

Title: Markov Game for CV Joint Adaptive Routing in Stochastic Traffic Networks: A Scalable Learning Approach
Authors: Shan Yang, Yang Liu
Abstract: This study proposes a learning-based approach to tackle the challenge of joint adaptive routing in stochastic traffic networks with Connected Vehicles (CVs). We introduce a Markov Routing Game (MRG) to model the adaptive routing behavior of all vehicles in such networks, thereby incorporating both competitive route choices and real-time decision-ma...
Keywords: Markov routing game; Connected vehicles; Joint adaptive routing; Mean-field multi-agent reinforcement learning; Stochastic traffic network

By |2024-07-30T15:44:52-04:00June 17, 2024||0 Comments
Read More

Podium Session 6: Estimating Markov Chain Mixing Times: Convergence Rate Towards Equilibrium of a Stochastic Process Traffic Assignment Model

Title: Estimating Markov Chain Mixing Times: Convergence Rate Towards Equilibrium of a Stochastic Process Traffic Assignment Model
Authors: Takamasa Iryo, David Watling, Martin Hazelton
Abstract: Network equilibrium models have been extensively used for decades. The rationale for using equilibrium as a predictor is essentially that (i) a unique and globally stable equilibrium point is guaranteed to exist, and (ii) the transient period over which a system adapts to a change is sufficiently short in time that it can be neglected. However, we ...
Keywords: Markov chain mixing time; Day-to-day dynamics; Stochastic traffic assignment process

By |2024-08-03T03:21:49-04:00June 17, 2024||0 Comments
Read More

Podium Session 6: A Day-to-Day Dynamical Approach to the Most Likely User Equilibrium Problem

Title: A Day-to-Day Dynamical Approach to the Most Likely User Equilibrium Problem
Authors: Jiayang Li, Qianni Wang, Liyang Feng, Jun Xie, Yu (Marco) Nie
Abstract: The lack of a unique user equilibrium (UE) route flow in traffic assignment has posed a significant challenge to many transportation applications. The maximum-entropy principle, which advocates for the consistent selection of the most likely solution, is often used to address the challenge. Built on a recently proposed day-to-day (DTD) discrete-tim...
Keywords: Maximum entropy; Traffic assignment; Cumulative logit; Day-to-day dynamical model; Proportionality condition

By |2024-08-03T03:27:11-04:00June 17, 2024||0 Comments
Read More

Podium Session 6: A Generalized Rationally Inattentive Route Choice Model with Non-uniform Marginal Information Costs

Title: A Generalized Rationally Inattentive Route Choice Model with Non-uniform Marginal Information Costs
Authors: Bo Zhou, Ronghui Liu
Abstract: Information consumes attention. In the information-rich society, a wealth of information can support decision-making, but it can also create poverty of attention to and inability to make the best use of information. This study applies the theory of rational inattention in modelling traveller’s route choice behaviour, where the attention (costs) to ...
Keywords: Route choice; Rational inattention; Non-uniform marginal information costs; Closed-form expression

By |2024-08-03T03:15:13-04:00June 17, 2024||0 Comments
Read More
Go to Top