Skip to main content

Advances, Systems and Applications

Table 3 Parameters setting about RL algorithms

From: Computation offloading strategy based on deep reinforcement learning for connected and autonomous vehicle in vehicular edge computing

Description

Parameter

Value

Learning rate

α

0.01

Discount factor

γ

0.9

Trace decay rate

λ

0.5

Initial temperature

θ

0.9

Number of hidden layers

 

2

Number of nodes for the first hidden layer

 

20

Number of nodes for the second hidden layer

 

20

Activation function for hidden layers

 

ReLU

Maximum replay memory size

|D|

500

Minibatch size

 

300

Parameter updating frequency for target DQN

ι

10