Reinforcement Learning to Reach Equilibrium Flow on Roads in Transportation System
Ref: CISTER-TR-190612 Publication Date: 6, Mar, 2019
Reinforcement Learning to Reach Equilibrium Flow on Roads in Transportation SystemRef: CISTER-TR-190612 Publication Date: 6, Mar, 2019
Traffic congestion threats the vitality of cities and the welfare of citizens. Transportation systems are using various technologies to allow users to adapt and have a different decision on transportation modes. Modification and improvement of these systems affect commuters’ perspective and social welfare. In this study, the effect of equilibrium road flow on commuters’ utilities with a different type of transportation mode will be discussed. A simple network with two modes of transportation will be illustrated to test the efficiency of minority game and reinforcement learning in commuters’ daily trip decision making based on time and mode. The artificial society of agents is simulated to analyze the results.
14th International Conference on Software Technologies (DSIE 2019), pp 60-65.