Search found 2003 matches

by Michel
Thu Jul 18, 2019 8:17 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Self-taught AI solves Rubik's cube
Replies: 15
Views: 485

Re: Self-taught AI solves Rubik's cube

Maybe this link works? https://www.nature.com/articles/s42256-019-0070-z.epdf?referrer_access_token=N-2bVrGfe-vTWeBW8R9w7NRgN0jAjWel9jnR3ZoTv0Osb8UCgUm5AQaSCMHWqWzspuy7oBsxRTU7jhKFTJ7Yw0YLdphdowkOldHTOgO6r7LITZumbh-rVKHPZPHRRHq9hW0eYsZa_6P7Hp8fqkvYNqp06H9F-kAxQ7LFB6aVHrdlvzZO2rEMVWxxBI8Qa1iefOIgO3pi...
by Michel
Thu Jul 18, 2019 7:06 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Self-taught AI solves Rubik's cube
Replies: 15
Views: 485

Re: Self-taught AI solves Rubik's cube

I've seen this video, probably some ad hoc solution, but funny: https://www.youtube.com/watch?v=f9smvQ5fc7Q 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 :...
by Michel
Thu Jul 18, 2019 3:37 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Self-taught AI solves Rubik's cube
Replies: 15
Views: 485

Re: Self-taught AI solves Rubik's cube

Daniel Anulliero wrote:
Thu Jul 18, 2019 3:32 pm
Fake , reversed video 😊😉
:)
by Michel
Thu Jul 18, 2019 12:43 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Self-taught AI solves Rubik's cube
Replies: 15
Views: 485

Re: 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. 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 heuris...
by Michel
Sat Jul 13, 2019 1:46 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish patches
Replies: 13
Views: 848

Re: Stockfish patches

The problem is Stockfish maintainers seem to be trigger happy with any microscopic elo gainer heuristic patch, but when it comes to bug fixes, that pr sits there for weeks. The problem is that people often disagree what constitutes a bug (is showing a +5 score in a draw position a bug?). Moreover i...
by Michel
Sat Jul 13, 2019 12:01 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish patches
Replies: 13
Views: 848

Re: Stockfish patches

playing 40000 games for every 2 consecutive versions even now will give an unbiased estimate with a possible mistake of 2 elo. Getting an accurate elo assessment of patches (or to do any kind or research at all) was never a goal of fishtest. The idea is that the considerable ressources needed for s...
by Michel
Sat Jul 13, 2019 9:12 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish patches
Replies: 13
Views: 848

Re: Stockfish patches

They give elo estimate for every change and if you add all the estimates that they publish the elo improvement shouls be clearly higher. You have a basic misunderstanding of statistics. The elo estimate calculated by fishtest is (median) unbiased over all patches (both failing and passing). In othe...
by Michel
Sat Jun 15, 2019 8:19 am
Forum: Computer Chess Club: General Topics
Topic: Polyglot 64-bit
Replies: 23
Views: 1975

Re: Polyglot 64-bit

Is it not sufficient to replace all int's in the sources book*.c which obviously refer to some position in the book with uint64? I may take up maintaining polyglot again. I find it a shame that polyglot book files after all these years still do not contain a header (for copyright messages, variants,...