Easily scalable approaches to reinforcement learning, by @ilyasut & co. Interesting thing: the algorithm appears very simple, & v. powerfulpic.twitter.com/6RMbuQtBSW
-
-
-
I wonder if this is faster than gradient descent/nature gradient for quantum states represented as neural networks
End of conversation
New conversation -
-
-
Kenneth Stanley's excellent talk "The Myth of the Objective" comes to mind: https://www.youtube.com/watch?v=dXQPL9GooyI …
-
I've watched it before. It's a nice talk - but there's a large number of interesting activities which do have an objective.
End of conversation
New conversation -
-
-
ES reduces to SPSA here. I remember when I used it for quantum tomography thinking why is this not more widely known?
-
Turns out, it has just been generalized and given different names...
End of conversation
New conversation -
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.