News for hackers. Stuff that matters.
Re:Deep Mind Playing Montezuma's Revenge with Intrinsic Moti... by dang on Wednesday June 08, 2016 @01:53PM (#11864120)
Given that this is what the paper (linked by jerf) says:

within a fraction of the training time, our agent explores a significant portion of the first level and obtains significantly higher scores than previously published agents

... it's probably just the usual hype.

There are no comments on this comment yet.