search

LantaoYu / SeqGAN

Implementation of Sequence Generative Adversarial Nets with Policy Gradient
2.08k stars 711 forks source link

what the 'start state s0' exactly is? #41

Open shaomai00 opened 6 years ago

shaomai00 commented 6 years ago

I saw 'generate a sequence from the start state s0 to maximize its expected end reward ...' in the paper. I'm wondering what the s0 exactly mean? In the code, I see the START_TOKEN=0 and h0=zeros,which one is start state?

EternalFeather commented 6 years ago

@shaomai00 I think START_TOKEN here is the first input to generator's LSTM model and furthermore h0 represents the initialization of hidden state and cell state in LSTM structure.