Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning

Table 3

Comparison of two methods’ PHR values.

OD pair	Morning peak		Evening peak
	Traditional method	New method	Traditional method	New method
(3, 11)	32.25%	17.93%	27.79%	11.42%
(5, 16)	24.43%	11.34%	31.64%	15.03%
(4, 17)	32.73%	21.52%	46.19%	20.49%
(5, 11)	25.50%	8.65%	28.61%	15.01%
(9, 10)	22.18%	16.79%	18.77%	10.12%
(9, 5)	46.23%	18.11%	17.98%	12.38%