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
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.