https://danijar.com/project/dreamerv3/ ← scaling this will give ASI (it will still have limitations, but that’s irrelevant, it’s enough to beat us if it doesn’t destroy the lab during training)
(not as fast as future algorithms, but still a hell of a lot faster than scaling mere autoregressive transformers)
https://danijar.com/project/dreamerv3/ ← scaling this will give ASI (it will still have limitations, but that’s irrelevant, it’s enough to beat us if it doesn’t destroy the lab during training)
(not as fast as future algorithms, but still a hell of a lot faster than scaling mere autoregressive transformers)