Search found 211 matches

by asanjuan
Thu Aug 31, 2017 12:51 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Ab-initio evaluation tuning
Replies: 51
Views: 10293

Re: Ab-initio evaluation tuning

The only drawback then is that you need to determine k again for the next run. No. Continue with the same K. There's no need to determine K. K is introduced to define a scale (Are you using centipawns, milipawns... quarter of a pawn?). If you are simply starting a new evaluation function, forget K....
by asanjuan
Thu Aug 31, 2017 12:13 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Ab-initio evaluation tuning
Replies: 51
Views: 10293

Re: Ab-initio evaluation tuning

[...] you are fitting game outcomes (1, 0 or 0.5) over f(x) = 1/(1+exp(-k*x)) The pawn value shoud be the result of the optimisation process, not an arbitray number. Your goal is to minimize that function, not to obtain 1.00 for the pawn value, wich is a "cosmetic" result. So: you need to tune ALL ...
by asanjuan
Thu Aug 31, 2017 11:02 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Ab-initio evaluation tuning
Replies: 51
Views: 10293

Re: Ab-initio evaluation tuning

There's no need to do that. You are biasing the result. The function is not arbitrary at all. Probably if the resulting "real" value for the pawn should be less than a pawn, the regression algorithm will lower the rest of the pieces to fit the value of the whole set to the game outcomes. I could be...
by asanjuan
Thu Aug 31, 2017 10:48 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Ab-initio evaluation tuning
Replies: 51
Views: 10293

Re: Ab-initio evaluation tuning

There's no need to do that. You are biasing the result. The function is not arbitrary at all. Probably if the resulting "real" value for the pawn should be less than a pawn, the regression algorithm will lower the rest of the pieces to fit the value of the whole set to the game outcomes. I could be...
by asanjuan
Thu Aug 31, 2017 10:27 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Ab-initio evaluation tuning
Replies: 51
Views: 10293

Re: Ab-initio evaluation tuning

4. In the evaluation, I have fixed the value of a pawn in the end game (VALUE_P_EG) at 256. This fixes the scale for the evaluation, which is otherwise arbitrary. There's no need to do that. You are biasing the result. The function is not arbitrary at all. Probably if the resulting "real" value for...
by asanjuan
Thu Jul 27, 2017 1:06 pm
Forum: Computer Chess Club: General Topics
Topic: Skipper update
Replies: 47
Views: 9699

Re: Skipper update

First of all: my apologies for bringing up this thread again, but I'm extremely surprised by this sentence: No Skipper does no do hash cut offs. For it uses Zobrist keys so it can't trust the hash move anymore because of hash collisions. And I want to avoid spending time on errors which were caused ...
by asanjuan
Thu Jul 06, 2017 7:11 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: LMR - [for starters] - [Advance] and [Expert]
Replies: 25
Views: 9577

Re: LMR - [for starters] - [Advance] and [Expert]

how did you get the values of the reductions table? table[depth][movecount] last year I was fooling around with a formula to fill a similar table, but nothing succeeded. I have a very simple approach (maximum reduction of 3 plys) and I couldn't get nothing better with a table with heavy reductions l...
by asanjuan
Thu Jun 22, 2017 10:55 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Cooking Cheese with Texel's tuning method
Replies: 13
Views: 3680

Re: Cooking Cheese with Texel's tuning method

I don't have time to work in my own engine, so let's help others instead. :) Thanks, I hope you will find more time. 1. Try to have equal or close to equal distribution of draws, wins and loses results. 2. More varied openings 3. More positions 4. Collect positions having more common evaluation fea...
by asanjuan
Wed Jun 21, 2017 8:58 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Cooking Cheese with Texel's tuning method
Replies: 13
Views: 3680

Re: Cooking Cheese with Texel's tuning method

I don't have time to work in my own engine, so let's help others instead. :) 1. Try to have equal or close to equal distribution of draws, wins and loses results. 2. More varied openings 3. More positions 4. Collect positions having more common evaluation features i.e training positions have passers...
by asanjuan
Thu May 05, 2016 8:46 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to speed up my engine
Replies: 88
Views: 19248

Re: How to speed up my engine

Search over ALL captures adds an extra overhead that you don't need. For example, you can discard losing captures in the quiescence search because you will surely stand pat in the next ply. Check that you are doing well the stand pat. I suggest you to implement a SEE function and discard moves wher...