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

Table 4

The statistical results of deterministic capacities.

OD pair	Serial number of paths	Link sequence	Mean flow	Flow standard deviation	Mean travel time	Time standard deviation
1-3	9	1-5-7-10-16	341.92	8.1509	51.975	0.5202
	10	1-5-8-14-16	34.67	3.6764	52.1231	0.352
	11	1-6-12-14-16	20.92	2.9565	52.1714	0.2675
	12	1-6-13-19	97.08	6.897	52.063	0.564
	13	2-17-7-10-16	0.24	0.5527	55.5151	0.3316
	14	2-17-8-14-16	0.17	0.4277	55.6632	0.3063
4-2	15	3-5-7-9-11	302.15	5.4926	49.7345	0.4098
	16	3-5-8-14-15	4.52	1.4318	49.9226	0.254
	17	3-5-7-10-15	37.09	3.4085	49.7746	0.4377
	18	3-6-12-14-15	1.19	1.2768	49.971	0.1818
	19	4-12-14-15	67.05	4.0982	49.7898	0.3518