Closed And-93 closed 2 years ago
The reward is the difference between the current wait time and the previous wait time? Essentially, the lesser the wait time more the reward would be
thank you, by chance is there any thesis or file that best describes all this your work that maybe I can ask?
Inviato da Postahttps://go.microsoft.com/fwlink/?LinkId=550986 per Windows
Da: Krishna P @.> Inviato: giovedì 3 febbraio 2022 13:48 A: @.> Cc: @.>; @.> Oggetto: Re: [krishnaph23/Smart-Traffic-Light-Controller-using-Deep-Reinforcement-Learning] Reward (Issue #2)
The reward is the difference between the current wait time and the previous wait time? Essentially, the lesser the wait time more the reward would be
— Reply to this email directly, view it on GitHubhttps://github.com/krishnaph23/Smart-Traffic-Light-Controller-using-Deep-Reinforcement-Learning/issues/2#issuecomment-1028955250, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AXOVQTSRNJLDZAU66FR2PNLUZJ2P3ANCNFSM5NO2DZSA. Triage notifications on the go with GitHub Mobile for iOShttps://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Androidhttps://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you authored the thread.Message ID: @.***>
how is the reward calculated? Could you tell me what data the reward takes into account?