[Retracted] Application of Deep Reinforcement Learning Algorithm in Uncertain Logistics Transportation Scheduling

Table 1

The performance of different strategies in uncertain logistics systems.

Strategy	Request served	Distance (km)	Computation
Optimal	200.00	3742.29	6.00 h
DRL-greedy	196.17	5855.68	0.51 s
DRL-sample@128	200.00	4612.84	3.96 s
DRL-sample@1k	200.00	4183.75	38.12 s
DRL-sample@13k	200.00	3966.61	379.44 s
DRL-sample@1 min	200.00	4139.84	60.00 s
MIP@ 1 min	200.00	10536.06	60.00 s
M-MOEA/D@ 1 min	198.03	4385.92	60.00 s
MIP@ 10 min	200.00	6150.25	600.00 s
M-MOEA/D@10 min	199.56	4004.19	600.00 s
MIP@60 min	200.00	3878.55	1.00 h
M-MOEA/D@60 min	200.00	3936.62	1.00 h