@admittedlyhuman Well, in one case I analyzed, it turned out that replacing the NN with a linear evaluator worked better.
@admittedlyhuman I don’t know… the approach seems completely obvious to me, given the state of the art in game-learning programs.
-
-
@Meaningness maybe you should do more obvious things and bask in the glory then -
@admittedlyhuman I often think you are right! I have chosen to do obscure things that I hope have enormous leverage in the long run, instead - 5 more replies
New conversation -
-
-
@admittedlyhuman I and many other people published papers with basically the same architecture in the 1980s.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.