Research Article

A Day-to-Day Route Choice Model Based on Reinforcement Learning

Table 5

The statistical results of random capacities.

OD pairSerial number of pathsLink sequenceMean flowFlow standard deviationMean travel timeTime standard deviation

1-391-5-7-10-16291.1116.965752.52732.8096
101-5-8-14-1648.76.379453.33682.4696
111-6-12-14-1637.065.928653.56862.1972
121-6-13-19117.411.884153.01732.2925
132-17-7-10-160.640.772255.30732.5127
142-17-8-14-160.090.287656.11672.1885

4-2153-5-7-9-11260.9614.456449.79082.3642
163-5-8-14-155.552.138551.23761.7302
173-5-7-10-1537.035.170750.42821.8506
183-6-12-14-152.451.665951.46951.4769
194-12-14-15106.0114.146150.36462.9827