I want to implement a DDPG method and obviously, the action space will be continuous. I have three outputs. The first output should be zero or a value between 200 and 400, and the other outputs have similar conditions. I don't know how can I implement this condition in the layers and activation functions. Should I use a binary activation before the scaled sigmoid function? How can I scale the activation function for this example?

(a1 = 0) or (200 < a1 < 400)
(a2 = 0) or (100 < a2 < 500)
(a3 = 0) or (200 < a3 < 1000)


generally the approach is to have a separate head. For example, imagine you have latent vector $z_k$, you would output two values: $h(z_k)$ and $f(z_k)$ where $0 \leq h \leq 1$ and $b_0 \leq f \leq b_1$ where $b_0$ and $b_1$ are your bounds.

In thios setup, during inference you would check $h_k$ and if its greater than some threshold (usually .5), youd evaluate/output $f_k$.

In this case your loss would look something like $L_i = L_i^{(1)}(h_i, y_i)+y_i*L_i^{(2)}(f_i,v_i)$ where $(y,v)$ are your labels, and the $L$'s are your loss of choice.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.