A simple question about the code about q-transformer HOT 2 CLOSED

@KID0031 hey thanks for your interest

yes you are right that a linear projection would probably do fine there as well. i'm following the weight tied output embedding technique from earlier transformer architectures (which in theory should allow the network to learn better embeddings), but that has been shown to be unnecessary

i'll make it an option to do it the way you describe

from q-transformer.

@KID0031 try setting this to False

on reflection, i think i had a bug in the weight tied action bin embeddings, so thanks for raising this

from q-transformer.