Search found 795 matches

by Joerg Oster
Thu Jan 07, 2021 5:10 pm
Forum: Computer Chess Club: General Topics
Topic: Laskas parameter optimizer
Replies: 4
Views: 804

Re: Lakas parameter optimizer

Run an optimization combining search and evaluation parameters with promising result. Will you give them a try at Fishtest? What should I do, I am not familiar with Fishtest. Fork the official repo. https://github.com/official-stockfish/Stockfish Create a new branch with your changes. Create an acc...
by Joerg Oster
Thu Jan 07, 2021 10:14 am
Forum: Computer Chess Club: General Topics
Topic: Laskas parameter optimizer
Replies: 4
Views: 804

Re: Lakas parameter optimizer

Ferdy wrote:
Thu Jan 07, 2021 4:35 am
Run an optimization combining search and evaluation parameters with promising result.
Will you give them a try at Fishtest?
by Joerg Oster
Sat Jan 02, 2021 10:10 am
Forum: Computer Chess Club: General Topics
Topic: Wasp 4.5 Released
Replies: 20
Views: 1599

Re: Wasp 4.5 Released

Thank you.
by Joerg Oster
Tue Dec 29, 2020 3:18 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Suggesting newer Neural Networks
Replies: 5
Views: 1559

Re: Suggesting newer Neural Networks

I think the first team that will be able to train and use multiple specialized nets in relevant way within an engine will lead the computer chess for many years. I don’t think that is the way to go at all. Why using many specialised nets when a bigger net can learn everything. The only thing you mi...
by Joerg Oster
Sat Dec 26, 2020 11:26 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: question about gensfen
Replies: 9
Views: 486

Re: question about gensfen

You need some randomness for variety and this is often controlled by the "temperature" parameter for MCTS-NN reinforcement learning. I wouldn't worry about the final score being assigned to all positions as long as the randomness (temperature) is limited to a reasonable value. I use a similar appro...
by Joerg Oster
Sat Dec 26, 2020 4:14 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: question about gensfen
Replies: 9
Views: 486

Re: question about gensfen

You need some randomness for variety and this is often controlled by the "temperature" parameter for MCTS-NN reinforcement learning. I wouldn't worry about the final score being assigned to all positions as long as the randomness (temperature) is limited to a reasonable value. I use a similar appro...
by Joerg Oster
Thu Dec 24, 2020 9:46 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: FRC in CECP
Replies: 31
Views: 1860

Re: FRC in CECP

I don't understand the value proposition here. The user decides (via the GUI) when engines resign or draw. And the way it's done is completely standard (score <= -Threshold for N moves by any one side for resign, |score| <= Threshold for N moves for draw). What else do you need ? And if you have so...
by Joerg Oster
Tue Dec 22, 2020 7:55 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Position Causes Stockfish and Komodo To Crash
Replies: 135
Views: 9545

Re: Position causes StockFish and Komodo to crash.

Thanks. It seems I was wrong. In your position SF does find the ep move. Then I wonder why it does not consider the ep move in the parentless position... Why generating an illegal move? Why do you consider the ep move illegal? Because this kind of move can NEVER occur in a legal game of chess. So I...
by Joerg Oster
Tue Dec 22, 2020 6:55 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Position Causes Stockfish and Komodo To Crash
Replies: 135
Views: 9545

Re: Position causes StockFish and Komodo to crash.

Hello Michel: An interesting issue here https://github.com/official-stockfish/Stockfish/issues/3270 SF move generation assumes (correctly it seems) that in a game an escape move can never be an ep move. But of course one can create positions (without parent) in which there is an escape move which i...
by Joerg Oster
Sat Dec 19, 2020 9:41 am
Forum: Computer Chess Club: General Topics
Topic: SFNNUE Fails!! In this Positions!!
Replies: 60
Views: 14957

Re: SFNNUE Fails!! In this Positions!!

There is no such rule. One can play as he wishes. That's exactly what I've been saying :shock: You're the one saying the shortest mate should be played, as if there was such a rule, as if the winning player couldn't play as they wish. Sure, when humans are playing. But from engines (or should I say...