The symbol-manipulating algorithm that is at the heart of the Rubik’s cube solving abilities of today’s hybrid model from @OpenAI: https://web.archive.org/web/20150226041111/http://kociemba.org/cube.htm …
-
Is MCTS considered a system 1 approach? Deepcube definitely uses it in its algorithm alongside DRL which achieves the autodidactic iteration part.
DeepCube also uses A* search, as classical as they come. I find System I/II a bit fuzzy, but certainly would not count MCTS as system I; it requires an enormous amount of very deliberate computation. It's more like System II on steroids.
-
-
Here is my position. System II deliberate cognitive processes can be simulated on system I hardware. This is what biological brains do. For silicon, there no need for a virtual machine for System II.
-
and here is my position: you can't get the system as a whole to work unless some components are in some fashion an implementation of the machinery of symbol-manipulation, e.g. variables, binding, and operations over variables.
- 3 more replies
New conversation -
-
-
It just occurred to me that the MCTS component is not necessary for the solver part. A human solver does not need to do tree search to solve a cube. This is only need to minimize moves.
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.