News for hackers. Stuff that matters.
Re:Human-level control through deep reinforcement learning by nl on Wednesday February 25, 2015 @05:40PM (#9110277)
The most interesting thing about this is that it shows significant progress towards goal-oriented AI. The fact this system is effectively learning what "win" means in the context of a game is something of a breakthrough.
Re:Human-level control through deep reinforcement learning by eveningcoffee on Wednesday February 25, 2015 @06:49PM (#9110563)
I do not think that it figures out "what the win is" as the score parameter is explicitly made available to the algorithm.

In some sense this paper even demonstrates that how simple the problem actually is.

I think more important question is that what else can be modelled as such problem.

Re:Human-level control through deep reinforcement learning by Houshalter on Wednesday February 25, 2015 @05:52PM (#9110334)
Reinforcement learning is not new. The same algorithm was used in the 90s to beat backgammon. The only notable thing is they are using raw pixels and vision to play the games.