Table 2 Default parameter settings for HAMEDA model.

From: Deep reinforcement learning based low energy consumption scheduling approach design for urban electric logistics vehicle networks

Parameters

Value

Parameters

Value

B

512

\({N_{epoch}}\)

500

\({N_{steps}}\)

500

\({d_x}\)

2

optimizer

Adam

learning rate

0.0001

\(\varpi\)

8

L

3

\({d_k}\)

64

\({d_h}\)

128

decaying rate

0.995

\(\alpha\)

0.05

Back to article page