Skip to main content

Table 2 Critic network structure

From: A proposal for adaptive cruise control balancing followability and comfortability through reinforcement learning

Network structure of critic

Name

State path

Action path

InputLayer

7ā€‰Ć—ā€‰1ā€‰Ć—ā€‰1

1ā€‰Ć—ā€‰1ā€‰Ć—ā€‰1

FullyConnectedLayer

fc21

fc51

ReluLayer

relu21

ā€“

FullyConnectedLayer

fc22

ā€“

AdditionLayer

add2

ReluLayer

relu22

FullyConnectedLayer

fc23

ReluLayer

relu23

FullyConnectedLayer

fc24