Zerush@lemmy.ml to Technology@lemmy.ml · 11 months agoUnpacking the hype around OpenAI’s rumored new Q* modelwww.technologyreview.comexternal-linkmessage-square14fedilinkarrow-up138arrow-down18
arrow-up130arrow-down1external-linkUnpacking the hype around OpenAI’s rumored new Q* modelwww.technologyreview.comZerush@lemmy.ml to Technology@lemmy.ml · 11 months agomessage-square14fedilink
minus-squareQ*Bert Reynolds@sh.itjust.workslinkfedilinkarrow-up13·edit-211 months agoIt’s probably based on Q learning, which has been around for 30+ years, and I’m guessing the star is a nod to A* because it’s an optimization of some kind.
It’s probably based on Q learning, which has been around for 30+ years, and I’m guessing the star is a nod to A* because it’s an optimization of some kind.