danijar / dreamerv2

Mastering Atari with Discrete World Models

Home Page:https://danijar.com/dreamerv2

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Batch size = 16?

mctigger opened this issue · comments

dataset: {batch: 16, length: 50}

Hi Danijar,
do I understand correct that this line should have batch = 50 to to have same hyperparameters as in the paper? I am asking because I want to investigate why my own PyTorch implementation is slower.

Yep, the defaults in the repo here are tuned for getting quick results (and top performance is still high). The hparams in the paper are a bit different.