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

Table 2

The paths in the third test network.

OD pair	Serial number of paths	Link sequence	OD pair	Serial number of paths	Link sequence
1-2	1	1-5-7-9-11	4-2	15	3-5-7-9-11
	2	1-5-7-10-15		16	3-5-8-14-15
	3	1-5-8-14-15		17	3-5-7-10-15
	4	1-6-12-14-15		18	3-6-12-14-15
	5	2-18-11		19	4-12-14-15
	6	2-17-7-9-11
	7	2-17-7-10-15
	8	2-17-8-14-15
1-3	9	1-5-7-10-16	4-3	20	3-5-7-10-16
	10	1-5-8-14-16		21	3-5-8-14-16
	11	1-6-12-14-16		22	3-6-12-14-16
	12	1-6-13-19		23	3-6-13-19
	13	2-17-7-10-16		24	4-12-14-16
	14	2-17-8-14-16		25	4-13-19