## Self-taught AI solves Rubik's cube

Discussion of chess software programming and technical issues.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Michel
Posts: 2087
Joined: Sun Sep 28, 2008 11:50 pm

### Self-taught AI solves Rubik's cube

https://www.nature.com/articles/s42256-019-0070-z

I have not quite understood yet what they do exactly.
Ideas=science. Simplification=engineering.
Without ideas there is nothing to simplify.

Michel
Posts: 2087
Joined: Sun Sep 28, 2008 11:50 pm

### Re: Self-taught AI solves Rubik's cube

Michel wrote:
Thu Jul 18, 2019 12:35 pm
https://www.nature.com/articles/s42256-019-0070-z

I have not quite understood yet what they do exactly.
Ok the use a NN to provide an estimated solution time. The NN is trained to match the estimated solution time to the one estimated from a 1-ply search. In chess this an old idea (match the heuristic evaluation function to the result of a 1-ply search).
Ideas=science. Simplification=engineering.
Without ideas there is nothing to simplify.

Michel
Posts: 2087
Joined: Sun Sep 28, 2008 11:50 pm

### Re: Self-taught AI solves Rubik's cube

Ideas=science. Simplification=engineering.
Without ideas there is nothing to simplify.

Daniel Shawul
Posts: 3824
Joined: Tue Mar 14, 2006 10:34 am
Location: Ethiopia
Contact:

### Re: Self-taught AI solves Rubik's cube

Can it beat this guy though who solves 17x17x17 cube in about 2 hours ? https://www.youtube.com/watch?v=7ChuKKL2PpU

I would like to understand what makes it a unique challenge. From what I understood from the abstract

- single goal state
- solved in reverse with root node being that single goal state (i.e. solved state)
- finds shortest path 60% of the time

Daniel

Daniel Shawul
Posts: 3824
Joined: Tue Mar 14, 2006 10:34 am
Location: Ethiopia
Contact:

### Re: Self-taught AI solves Rubik's cube

Dumb reporter from jakarta post
In a world first, researchers at the University of California have developed a computer algorithm that can solve a Rubik's Cube without a neural network, machine learning techniques, "specific domain knowledge," or human assistance.
And this
By successfully being able to solve a Rubik's Cube without initially being trained on previous information, the DeepCubeA algorithm represents the gradual shift in machines from making carefully-directed computations to making those which appear to resemble human-like reasoning and decision-making.
Last edited by Daniel Shawul on Thu Jul 18, 2019 3:34 pm, edited 1 time in total.

Daniel Anulliero
Posts: 695
Joined: Fri Jan 04, 2013 3:55 pm
Location: Nice

### Re: Self-taught AI solves Rubik's cube

Daniel Shawul wrote:
Thu Jul 18, 2019 3:24 pm
Can it beat this guy though who solves 17x17x17 cube in about 2 hours ? https://www.youtube.com/watch?v=7ChuKKL2PpU

I would like to understand what makes it a unique challenge. From what I understood from the abstract

- single goal state
- solved in reverse with root node being that single goal state (i.e. solved state)
- finds shortest path 60% of the time

Daniel
Fake , reversed video

Daniel Shawul
Posts: 3824
Joined: Tue Mar 14, 2006 10:34 am
Location: Ethiopia
Contact:

### Re: Self-taught AI solves Rubik's cube

Failed for it

Michel
Posts: 2087
Joined: Sun Sep 28, 2008 11:50 pm

### Re: Self-taught AI solves Rubik's cube

Daniel Anulliero wrote:
Thu Jul 18, 2019 3:32 pm
Fake , reversed video
Ideas=science. Simplification=engineering.
Without ideas there is nothing to simplify.

mar
Posts: 2091
Joined: Fri Nov 26, 2010 1:00 pm
Location: Czech Republic
Full name: Martin Sedlak

### Re: Self-taught AI solves Rubik's cube

I've seen this video, probably some ad hoc solution, but funny:
The basic idea as I understand it is to solve inner faces first, then edges and the rest is solved just like a classic 3x3 cube.

(I admit that I never managed to solve a rubik's cube myself
Martin Sedlak

Michel
Posts: 2087
Joined: Sun Sep 28, 2008 11:50 pm

### Re: Self-taught AI solves Rubik's cube

mar wrote:
Thu Jul 18, 2019 4:39 pm
I've seen this video, probably some ad hoc solution, but funny: