ROBOMECH Journal

Table 1 Actor network structure

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

Network structure of actor
Name	State path
InputLayer	7 × 1 × 1
FullyConnectedLayer	fc11
ReluLayer	relu11
FullyConnectedLayer	fc12
ReluLayer	relu12
FullyConnectedLayer	fc13
ReluLayer	relu13
FullyConnectedLayer	fc14
TanhLayer	tanh11
ScalingLayer	scale = 2.5, bias = − 0.5

Back to article page