STEVE-1
STEVE-1 copied to clipboard
STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
I configure the envrionment on wsl Ubuntu20.04, my cuda version in nvidia-smi is 11.6 When I run ". run_agent/1_gen_paper_videos.sh" , an assertion error occurs: ( /home/lyh/STEVE-1/steve1/embed_conditioned_policy.py , buttons = pd['buttons'][0,...
Hi, do you provide the 54M dataset?
In the Appendix D.2 section of the paper, the Prior Training section, I understood how Steve-1 collected text-video pairs for training the Prior. I am particularly interested in two points...