Re:Gato – A Generalist Agent
by tootyskooty on Tuesday May 17, 2022 @04:53PM
(#31416154)
One important thing to note here is that this model was trained purely in a supervised fashion.
It would be interesting to see a paper at a similar scale that's based on reinforcement learning.
The reinforcement learning context (specifically the exploring part) gives a lot more opportunities to see the effects of positive/negative transfer.
That approach would of course be much more expensive, though.
[ Parent
| on HN ]
There are no comments on this comment yet.