search

junhyukoh / self-imitation-learning

ICML 2018 Self-Imitation Learning
MIT License
274 stars 41 forks source link

entropy in SIL policy loss #6

Open gabrieledcjr opened 5 years ago

gabrieledcjr commented 5 years ago

In the equation in the paper, there is no entropy term in the SIL policy loss, how come in the code there is one?

self.loss = self.pg_loss - entropy * self.w_entropy