Search found 81 matches

by Tony P.
Sun Feb 05, 2017 11:41 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deep Pink: a chess engine using deep learning
Replies: 20
Views: 6400

Re: Deep Pink: a chess engine using deep learning

Actually, I believe there will be a point in computer chess progress when search will no longer be divided into main and quiescent. Engines will, all the way from the root to the leaves, always prefer to dig deeper into those variations that 1) are looking the most promising so far and 2) their mode...
by Tony P.
Sun Feb 05, 2017 11:17 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deep Pink: a chess engine using deep learning
Replies: 20
Views: 6400

Re: Deep Pink: a chess engine using deep learning

2. "Players will choose an optimal or near-optimal move" is a bad assumption for the FICS dataset. Players will choose better than random moves, which is part of the theory. But for chess, even expert players are a poor "oracle," because they blunder from time to time and make suboptimal moves pret...
by Tony P.
Sun Feb 05, 2017 10:57 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deep Pink: a chess engine using deep learning
Replies: 20
Views: 6400

Re: Deep Pink: a chess engine using deep learning

Meh. Deep Pink has scored merely 30-35% of points in a match vs Sunfish, which is a simple and weak engine that's not even rated on CCRL (nor other official rating lists, I guess). Currently, the strongest of those chess engines whose evaluation is based on a neural network is Giraffe. It has achiev...
by Tony P.
Sun Feb 05, 2017 9:28 pm
Forum: Computer Chess Club: General Topics
Topic: CHEMICAL ENGINES
Replies: 4
Views: 1264

Re: CHEMICAL ENGINES

You're right in that I wasn't accurate when writing my previous post... Thank you for the clarifications! (I assume you meant supervised learning in your last 2 sentences.) But I feel that we're talking about somewhat different approaches to evaluation. You've described the tuning process for the st...
by Tony P.
Sun Feb 05, 2017 2:12 am
Forum: Computer Chess Club: General Topics
Topic: CHEMICAL ENGINES
Replies: 4
Views: 1264

Re: CHEMICAL ENGINES

Are you asking what these abbreviations mean in the context of chess programming? I think that: CMH = Countermove Heuristic MRL = Modular Reinforcement Learning These topics are too complex for me to understand; I hope you learn something useful from the linked articles. The word 'modular' in 'modul...
by Tony P.
Tue Jan 31, 2017 7:07 pm
Forum: Computer Chess Club: General Topics
Topic: Chess Performance enhancing drugs!
Replies: 47
Views: 5370

Re: A doctor´s point of view

Tal's intake of green tea might have had an extra purpose, though - relief of the aftermath of his other usual drinks :lol:
by Tony P.
Tue Jan 31, 2017 5:45 pm
Forum: Computer Chess Club: General Topics
Topic: Arasan 20.0
Replies: 16
Views: 3464

Re: Arasan 20.0

As the computer power goes slowly cheaper, I think that this will be an area of improvement of the engines at some point. I mean that of course an engine can be retuned to play more optimal against other engines. As always, while you have a system of improvement that works, is difficult at least ps...
by Tony P.
Tue Jan 31, 2017 1:40 am
Forum: Computer Chess Club: General Topics
Topic: Arasan 20.0
Replies: 16
Views: 3464

Re: Arasan 20.0

Congrats on the release! Btw, with the immense hardware power that allows to run blitz gauntlets fast enough nowadays, why do chess programmers still rely on the self-play result as an accurate measure of improvement? A gauntlet vs a mixture of opponents with different styles is so much closer to th...
by Tony P.
Mon Jan 30, 2017 6:18 pm
Forum: Computer Chess Club: General Topics
Topic: Chess Performance enhancing drugs!
Replies: 47
Views: 5370

Re: A doctor´s point of view

So I suggest to take just a cup of coffee in the morning before the game. With so many herbal teas available, I'm surprised to see a mental health expert suggest coffee. Is it really safe enough? Anyway, it has to be noted that you were likely talking about coffee without sugar, which is the right ...
by Tony P.
Mon Jan 30, 2017 5:48 pm
Forum: Computer Chess Club: General Topics
Topic: Why is the MIT License unpopular in chess programming?
Replies: 13
Views: 3891

Re: Why is the MIT License unpopular in chess programming?

Or asking the actual authors for a dual licence release, though that would probably cost money. I guess that's a pretty common way for SW authors to monetize their side projects without spending a lot on marketing, haha. To clarify, I don't mean to pressurize anyone into relicensing their code, and...