Integrating System Optimum and User Equilibrium in Traffic Assignment via Evolutionary Search and Multiagent Reinforcement Learning

Traffic assignment is fundamentally a tool for transportation planning. It allocates trips within the traffic network. However, modern uses of traffic assignment also include shorter time horizons and even real-time use (e.g., for route recommendation). In the latter case, it is interesting to recommend routes that are as close as possible to the system optimum. To compute an approximation of the optimal traffic assignment, we use a hybrid approach, in which an optimization process based on an evolutionary algorithm is combined with multiagent reinforcement learning. This has two advantages: first, the convergence is accelerated; second, the multiagent reinforcement learning resembles the adaptive route choice that drivers perform in order to seek the user equilibrium. Thus, the hybrid approach aims at incorporating both the system and the user perspectives in the traffic assignment problem. Results are encouraging: the combination of the evolutionary approach and the multiagent reinforcement learning accelerates the computation and delivers an efficient assignment in terms of travel time.