Why dilated_lstm and normal_lstm are exactly the same?

[Trinkle23897]

There is no difference between the two folders. ?

[jdubkim]

Thank you for your interest! We didn't update our recent version to our master branch. You should go to dLSTM branch dlstm_a2c folder to check the new one. However, our code still doesn't work. We're still on the progress, so please keep interests into our github repo.

[PeiYingjun]

Thank you for your interest! We didn't update our recent version to our master branch. You should go to dLSTM branch dlstm_a2c folder to check the new one. However, our code still doesn't work. We're still on the progress, so please keep interests into our github repo.

what do you mean by 'doesn't work', you mean the score doesn't increase after many episodes or the learning curve doesn't converge(ie, policy loss, value loss)? I've designed my own universal HRL algorithm similar to FuN, yet it didn't even converge.