Skip to Main Content
Table 3

DDPG RL agent architecture and hyperparameter settings

Actor
Critic
NN layerNeuronsActivationNeuronsActivation
Input Current state s N/A Current state s and action a N/A 
Hidden 1 16 RELU 32 RELU 
Hidden 2 16 RELU 32 RELU 
Hidden 3 RELU 32 RELU 
Output 1 [R1, R2] Sigmoid 1 [q-value] Linear 
Actor
Critic
NN layerNeuronsActivationNeuronsActivation
Input Current state s N/A Current state s and action a N/A 
Hidden 1 16 RELU 32 RELU 
Hidden 2 16 RELU 32 RELU 
Hidden 3 RELU 32 RELU 
Output 1 [R1, R2] Sigmoid 1 [q-value] Linear 
Close Modal

or Create an Account

Close Modal
Close Modal