Search found 17 matches

by KWRegan
Fri Feb 23, 2018 12:39 pm
Forum: Computer Chess Club: General Topics
Topic: Marcel Duchamp endgame "splits" engines / hash phe
Replies: 11
Views: 2407

Re: Marcel Duchamp endgame "splits" engines / hash

Indeed I had contempt=0; I forgot to mention that as a departure from the defaults.
by KWRegan
Mon Feb 19, 2018 9:04 pm
Forum: Computer Chess Club: General Topics
Topic: Marcel Duchamp endgame "splits" engines / hash phe
Replies: 11
Views: 2407

Marcel Duchamp endgame "splits" engines / hash phe

The final long section of an article on Marcel Duchamp which I wrote for the Gödel's Lost Letter weblog https://rjlipton.wordpress.com/2018/02/16/a-coupe-of-duchamp/ covers his only known composed endgame problem---different from the "corresponding squares" position which is the only other Duchamp e...
by KWRegan
Sat Jan 27, 2018 3:58 am
Forum: Computer Chess Club: General Topics
Topic: a second "grand" title
Replies: 23
Views: 5173

Re: a second "grand" title

1,000 good wishes to you and your daughter and daughter^2!

---Ken R.
by KWRegan
Thu Dec 07, 2017 5:04 am
Forum: Computer Chess Club: General Topics
Topic: Historic Milestone: AlphaZero
Replies: 193
Views: 76960

Re: Much weaker than Stockfish

Why don't they disclose what their evaluation is: that will be a big step towards knowing the truth. They can't. The evaluation is a sequence of numbers specifying myriad weights on umpteen-dozen layers of a neural network. This aspect (of the original AlphaGo) in contrast to Stockfish is addressed...
by KWRegan
Tue Nov 28, 2017 8:02 pm
Forum: Computer Chess Club: General Topics
Topic: "Intrinsic Chess Ratings" by Regan, Haworth -- seq
Replies: 9
Views: 2311

Re: "Intrinsic Chess Ratings" by Regan, Haworth --

Erik, it is interesting that your Graph 24 in section 4.3 shows the same general shape as mine at https://www.cse.buffalo.edu/~regan/chess/fidelity/data/IPR2600reg4yr.jpg which is for the bellwether 2600 level only. That is, it shows a fairly smooth downward from the late 1980s through about 2002 th...
by KWRegan
Tue Nov 21, 2017 12:54 pm
Forum: Computer Chess Club: General Topics
Topic: "Intrinsic Chess Ratings" by Regan, Haworth -- seq
Replies: 9
Views: 2311

Re: "Intrinsic Chess Ratings" by Regan, Haworth --

On the specific topic of rating inflation, the paper you want is actually the 2011 Regan-Haworth followup in which GM Bartlomiej Macieja joined us: https://www.cse.buffalo.edu/~regan/papers/pdf/RMH11b.pdf Plus this chart on my main page: https://www.cse.buffalo.edu//~regan/chess/fidelity/data/IPR260...
by KWRegan
Mon Nov 20, 2017 5:26 pm
Forum: Computer Chess Club: General Topics
Topic: "Intrinsic Chess Ratings" by Regan, Haworth -- seq
Replies: 9
Views: 2311

Re: "Intrinsic Chess Ratings" by Regan, Haworth --

Jean-Marc Alliot's paper linked by Walter Koroljow is a good one, especially for the idea of applying a Markov process. What he calls "ponderated conformance" is the same basic idea as what my papers call "scaled difference"; the main technical difference is that I treat essentially what he calls 1/...
by KWRegan
Sun Mar 27, 2016 1:56 am
Forum: Computer Chess Club: General Topics
Topic: Estimated Elo Perfect Play
Replies: 18
Views: 5152

Re: Estimated Elo Perfect Play

I follow others' use of two indicators that give wildly different answers, but which my "Intrinsic Performance Rating" metric combines into something reasonable. The two indicators individually do not depend on any details of my model---anyone using Guid-Bratko's or Charles Sullivan's TrueChess ( ht...
by KWRegan
Sun Feb 07, 2016 2:47 am
Forum: Computer Chess Club: General Topics
Topic: Oddity around depths 7-8 with Stockfish 6 & 7
Replies: 30
Views: 7920

Re: Oddity around depths 7-8 with Stockfish 6 & 7

I re-ran the data for Elo 2600--2800 after modifying one line of the Stockfish 7 code to forbid move-count-based pruning at PV nodes. Doing so greatly reduced the numerical issue shown by my tables at depth 5, but seems not to have completely removed it. I have updated my post https://rjlipton.wordp...
by KWRegan
Fri Jan 22, 2016 4:26 am
Forum: Computer Chess Club: General Topics
Topic: Oddity around depths 7-8 with Stockfish 6 & 7
Replies: 30
Views: 7920

Re: Oddity around depths 7-8 with Stockfish 6 & 7

Here's a "data dump" of likely cases---all from the Elo 2600+ player run in positions where Stockfish 7 at high depth says it is within 0.10 of equality. First comes a game tag and then the FENs before and after the played move, which is labeled in the former by the EPD opcode "sm". The anomaly occu...