There are (and should be) many different ways to assess generalization, but you might start with @LakeBrenden’s updates to my late 90’s work. And look at @dileeplearning’s work on how DQN fails in tiny changes to Atari games.
-
Internal products are still products, $100M is noteworthy given the basic research focus. The notion of using revenue/costs to assess scientific merit is rather unique to you. What lab is doing better by this metric? Has it historically been a precursor to larger innovation?
Just to clarify from my previous posts: I wasn't saying that DeepMind doesn't hype their work; they absolutely do. I was just questioning your criticism that they don't have a successful deep RL *commercial product*.
@Zergylord please reread; i absolutely did not judge the scientific value of DRL on $revenue. multiple paragraphs pointing out other limits, before economic analysis.
-
-
The article is about a recent release of financial information and you've connected that says to scientific prospects somehow. I know you've got lots of other reasons (many listed in the article), but that article made clear cost/revenue was one. What am I misrereading, exactly?
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.