We propose a route choice model in which traveler behavior is represented as utility maximizing assignment of flow across an entire network under conservation constraint. Substitution between routes depends on how much they overlap. The estimated considering the full set alternatives, and no generation required. Nevertheless, estimation requires only linear regression very fast. Predictions fro...

The use of reinforcement learning (RL) in multiagent scenarios is challenging. I consider the route choice problem, where drivers must choose routes that minimise their travel times. Here, selfish RL-agents must adapt to each others’ decisions. In this work, I show how the agents can learn (with performance guarantees) by minimising the regret associated with their decisions, thus achieving the...

The orienteering route choice problem involves finding the fastest route between two given points, with running speed determined by various properties of the terrain. In this study we consider only the effect of climbing or descent on running speed. If a runner’s pace p (the reciprocal of running speed) varies linearly with gradient m, the straight-line route is always fastest. This may be a re...

We study route choice behavior when travel time is uncertain. In this case, users do not minimize expected travel time but also take into account travel time variability. We collected survey data and analyze them with a method based on the ordered probit model. This allows us to have an ordinal as well as cardinal measures of risk aversion. Such an approach is therefore consistent with expected...