Re:Why traditional reinforcement learning will probably not ...
by AlphaSite on Wednesday October 21, 2020 @07:29PM
(#24853436)
I think the point huh is being mad is that individual people (or models) dot learn that way. Itβs not like models training models, all the way down.
[ Parent
| on HN ]
Re:Why traditional reinforcement learning will probably not ...
by the8472 on Wednesday October 21, 2020 @09:12PM
(#24853997)
Individual people are not trained from scratch. ML models often have to be (modulo fine-tuning) since the field is still young.
Re:Why traditional reinforcement learning will probably not ...
by mannykannot on Wednesday October 21, 2020 @09:45PM
(#24854142)
That's already changing. That we have only relatively recently moved beyond always starting from scratch might indicate that we are still in the Cambrian of AI, however...