esteveste / dreamerV2-pytorch

Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
17 stars 4 forks source link

learning curve or pretrained model #2

Closed initial-h closed 2 years ago

initial-h commented 2 years ago

Hi, Thanks for your reimplementation and open source. I think you must do some tests for these Atari games. I wonder do you have some records of learning curves or pretrained models that I can use to get a baseline score. Thanks very much!

esteveste commented 2 years ago

Hello, thanks for you issue. I placed a plot comparing learning the same atari game between the original and this implementation. I also placed a link for some pre-trained models. Hope it helps. Cheers!