Yes! Continually evolving task-specific loss functions is the gateway to 'full-time' learning where we can stop thinking of 'datasets' and start thinking of 'data-rich environments'. We're getting closer!
Nice work from OpenAI on evolving loss functions to quickly master new tasks: https://blog.openai.com/evolved-policy-gradients/ …pic.twitter.com/81YrU2VJMG
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.