fsoul
fsoul
Hi,Thanks for your great work. I wonder how large intrinsic reward is in a step when meeting a novel state.
And when I train then environment 'venture', the intrinsic reward seems normal(the loss would suddenly increase), but the extrinsic reward was always zero. Any solution?
helphelp
I also wonder whether it stills require virtualgl when running the code in the container
Sorry. I just saw the dockerfile in the raw branch.
Can you provide more instructions about how to run the docker of yours? The error message is "/bin/sh: 1: glxgears: not found".
> Hey everyone! I have a few questions on finetuning that I would love if you could answer: > > * Is a dataset size of 50-100 videos okay for...
Thanks a lot for replying! They are very helpful. I have one more question: so we don't need to use EMA model to train?