News for hackers. Stuff that matters.
Re:Google Cuts Its Giant Electricity Bill with DeepMind-Powe... by argonaut on Wednesday July 20, 2016 @03:48AM (#12127454)
Errr... No. Just no. Deep reinforcement learning is not some pixie dust that magically works for any problem with a reward function that you throw it at. It's astounding how commenters on HN think this is all "easy".
Re:Google Cuts Its Giant Electricity Bill with DeepMind-Powe... by dmos62 on Wednesday July 20, 2016 @08:15AM (#12128373)
This quickly went to you say this, I say this. These are very interesting statements, it would be nice if they were supported by citations.
Re:Google Cuts Its Giant Electricity Bill with DeepMind-Powe... by argonaut on Wednesday July 20, 2016 @10:24AM (#12129208)
The poster I was replying to is really the one who needs to prove that deep RL is super easy like they were claiming.