Dynamic Evolution of Multilevel Rail Transit Destination Choice Behavior Based on Disaggregate–Reinforcement Learning

To address the distribution of origin–destination (OD) passenger flow in multilevel rail transit complex network, we propose a simulation method based on travel behavior and reinforcement learning for travelers’ multilevel rail transit network destination choice behavior. First, we extended the node–place (NP) model into node–place–ridership (NPR) model as the ridership and the level of rail transit are introduced into the indicators. The place value is calculated based on the difference in the catchment area of stations at each level to construct an indicator system for stations. From the perspective of traveler behavior, a destination choice model is developed using the station’s NPR variables. Then, the Bush–Mosteller (BM) reinforcement learning model is employed to simulate the evolutionary mechanism of travelers’ destination choice behavior under the influence of group decision‐making characteristics, thereby designing an OD matrix convergence algorithm. The methodology’s validity is demonstrated through a case study involving a multilevel rail transit network in Guangzhou and Foshan, Guangdong Province. Results indicate that the approach effectively captures the choice behavior mechanisms of travelers within incomplete information contexts. The evolution of OD passenger flows between intracity, suburban city, and intercity stations exhibits distinct patterns; however, OD volumes between stations spanning different hierarchical levels remain consistently low (lower than 300) and stable. During the propagation and diffusion of travel‐related information throughout the network, the positive effect exerted by dominant stations demonstrates significantly greater transmission intensity than the negative effect associated with nondominant stations. The estimated result of the same‐level dummy in the destination choice model (0.527–0.825) indicates that the interchange barrier between interlevel OD is a major factor affecting the travel of multilevel rail users.