search

baturaysaglam / RIS-MISO-Deep-Reinforcement-Learning

Joint Transmit Beamforming and Phase Shifts Design with Deep Reinforcement Learning
MIT License
139 stars 39 forks source link

Optimization constraints #6

Closed vigorPan closed 1 year ago

vigorPan commented 1 year ago

Why the normalization of power can satisfy the constraints of the optimization equation? If there are other constraints, what should we do？

baturaysaglam commented 1 year ago

because the constraint states that you should get a power value smaller than or equal to the pre-specified power constraint value. normalizing the power will get you a value equal to the pre-specified constraint. hence, it satisfies the constraint. it is a bit sloppy but realizing this in the codebase is really hard. nonetheless, this version should work fine.

I cannot directly answer the second question without knowing which components they regard.