dreamerv2
dreamerv2 copied to clipboard
danijar
Mastering Atari with Discrete World Models
Dear author, After reading the code and the paper, I am confused about why Imagination MDP is introduced and why imagination horizon is needed. For example, with a trained world...
As per https://github.com/mgbellemare/Arcade-Learning-Environment/issues/440
I wanted to try out dreamerv2 on our own environment (or at least the examples) but unfortunately run into some issues along the way. The README example & Dockerfile use...
Hi, I found that in the Dreamerv3 codes, there is a 'prev_action' which is used for the imagine step. However, in Dreamerv2, it seems that the 'action' is used instead,...
I'm currently exploring the Dreamer models and papers and wanted to get some insight from the code. However, I'm encountering a few issues with reproducibility. I initially attempted to replicate...
Hi, I find your work really fascinating and I am trying to reproduce DayDreamer's results in A1 robot dog simulator. The simulator is the A1 robot in [Google motion imitation](https://github.com/erwincoumans/motion_imitation),...
# Why In 2023/01/20, I tried to run dreamerv2 by Docker, however, some errors occurred when building the docker image. The error details are as follows: 1. GPG error in...
Hey @danijar. I just noticed that the code is using `TruncNormal` as the actor distribution instead of `TanhNormal` as in v1. I wonder did you make some ablations on these...
When I was using your code, I only founded the Hyperparameters of Walker-Walk but Humanoid-Walk. In the official paper, it has the results of Humanoid-Walk Environment. So could you please...
Two issues on Dockerfile tensorflow:2.4.2-gpu has an issue on ``` RUN apt-get update && apt-get install -y \ ffmpeg \ libgl1-mesa-dev \ python3-pip \ unrar \ wget \ && apt-get...
