JORLDY icon indicating copy to clipboard operation
JORLDY copied to clipboard

Published 20 hours ago • verified publisher icon kakaoenterprise

R2D2 doesn't have reward as input ?

Open hlsafin opened this issue 2 years ago • 0 comments

I could be wrong about this, but looking at the implementation, it doesn't seem like it's taking in the previous reward alongside state and prev action into the LSTM, no? Was this a design decision?

hlsafin avatar Aug 08 '22 22:08 hlsafin