search

kakaoenterprise / JORLDY

Repository for Open Source Reinforcement Learning Framework JORLDY
Apache License 2.0
362 stars 49 forks source link

R2D2 doesn't have reward as input ? #216

Closed hlsafin closed 2 years ago

hlsafin commented 2 years ago

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?