search

baturaysaglam / RIS-MISO-PDA-Deep-Reinforcement-Learning

Joint Transmit Beamforming and Phase Shifts Design with Deep Reinforcement Learning Under the Phase-Dependent Amplitude Model
MIT License
67 stars 16 forks source link

Imperfect CSI #5

Closed AhdHazim closed 1 year ago

AhdHazim commented 1 year ago

Thank you so much for great contribution.

I am wondering about one thing while I read the code of this paper, which is that you have mentioned that you used Imperfect CSI, but unfortunately due to my ignorance I could not figure out how you represented the imperfect CSI in your code. I would be thankful if you can explain to me this point please.

baturaysaglam commented 1 year ago

it should be on this line if I'm not wrong.

AhdHazim commented 1 year ago

@baturaysaglam thank you so much for your kind reply!

Could you explain it for me more please as I could not understand why you divided by 2???

baturaysaglam commented 1 year ago

If you want to sample from a complex Gaussian, you have to divide the variance term by 2.

AhdHazim commented 1 year ago

Thank you so much!

Get Outlook for Androidhttps://aka.ms/AAb9ysg

From: Baturay Saglam @.> Sent: Friday, November 10, 2023 1:16:28 PM To: baturaysaglam/RIS-MISO-PDA-Deep-Reinforcement-Learning @.> Cc: Sabr, Ohood @.>; Author @.> Subject: Re: [baturaysaglam/RIS-MISO-PDA-Deep-Reinforcement-Learning] Imperfect CSI (Issue #5)

If you want to sample from a complex Gaussian, you have to divide the variance term by 2.

— Reply to this email directly, view it on GitHubhttps://github.com/baturaysaglam/RIS-MISO-PDA-Deep-Reinforcement-Learning/issues/5#issuecomment-1806199203, or unsubscribehttps://github.com/notifications/unsubscribe-auth/BDSWQXYQERQRNXEW6A26MY3YDZVPZAVCNFSM6AAAAAA7AEIRE6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQMBWGE4TSMRQGM. You are receiving this because you authored the thread.Message ID: @.***>