search

baturaysaglam / RIS-MISO-Deep-Reinforcement-Learning

Joint Transmit Beamforming and Phase Shifts Design with Deep Reinforcement Learning
MIT License
130 stars 37 forks source link

Questions in 'DDPG.py' and 'environment.py' #13

Closed ChaiShiMei closed 1 year ago

ChaiShiMei commented 1 year ago

Dear Mr. Baturay Saglam,

I have some questions regarding to 'DDPG.py' and 'environment.py' . In 'DDPG.py', I think the codes of lines 47-52 and 65-67 aiming to normalize the phase shift matrix are wrong. Because the norm of the phase after normalization is not equal to 1 ( Actually much less than 1).

In 'environment.py', in line 114 , is the power '**2' necessary? Because 'self.G.conjugate().T @ self.G' is already the power. Meanwhile, in line 90, why do you multiply the noise power 'self.awgn_var' with '(self.K - 1)'?

Could you please double-check these three places?

baturaysaglam commented 1 year ago

please take a look at here.