Search found 143 matches

by jkiliani
Tue Feb 05, 2019 7:44 am
Forum: Computer Chess Club: General Topics
Topic: Lc0 ... the GOOD and the BAD
Replies: 54
Views: 4825

Re: Lc0 ... the GOOD and the BAD

A0 does have a similar "tactical bug" to Lc0 (as shown in my other post http://talkchess.com/forum3/viewtopic.php?f=2&t=69799) but apparently it does not happen too often. I think Lc0 will end up being much stronger than A0 as there was not so much time spent on A0. If you look at the progress of S...
by jkiliani
Thu Dec 20, 2018 9:36 am
Forum: Computer Chess Club: General Topics
Topic: Smallnet (128x10) run1 progresses remarkably well
Replies: 24
Views: 2601

Re: Smallnet (128x10) run1 progresses remarkably well

But kais main point, I think, was that experimental runs should be as efficient as possible. Could eg tests20+30, and again test40 (if the aim is truly experimental as the name implies) be performed entirely on 128x10 (or smaller) nets, or does it not translate? test30 is an experimental run, and s...
by jkiliani
Thu Dec 20, 2018 1:15 am
Forum: Computer Chess Club: General Topics
Topic: Smallnet (128x10) run1 progresses remarkably well
Replies: 24
Views: 2601

Re: Smallnet (128x10) run1 progresses remarkably well

After Lc0 0.20 is released, test35 will be retired in favour of test40, a SE net of the same dimensions as test10 and test30, i.e. 256x20. That run is widely expected to significantly improve on test10. Again I hope TB rescoring will not be part of test40, now we know what A0's C(s) was. As far as ...
by jkiliani
Thu Dec 20, 2018 1:07 am
Forum: Computer Chess Club: General Topics
Topic: Smallnet (128x10) run1 progresses remarkably well
Replies: 24
Views: 2601

Re: Smallnet (128x10) run1 progresses remarkably well

Again, test40 with bignet. And then the master bignet? Well, I have no any knowledge of what you are doing, I wish you good luck and a fast success with test40. It has been quite conclusively shown that larger nets are more powerful in the end, they just require more resources to train. test10 was ...
by jkiliani
Thu Dec 20, 2018 12:45 am
Forum: Computer Chess Club: General Topics
Topic: Smallnet (128x10) run1 progresses remarkably well
Replies: 24
Views: 2601

Re: Smallnet (128x10) run1 progresses remarkably well

What is called smallnet in this thread is called test35, and its only real purpose is to test whether the SE (Squeeze-Excitation) Neural network architecture is implemented correctly in Lc0 0.20 Dev. So far it looks like that is the case, and SE nets are significantly stronger at the same network si...
by jkiliani
Sat Oct 20, 2018 5:27 am
Forum: Computer Chess Club: General Topics
Topic: Current TCEC Cup
Replies: 22
Views: 3373

Re: Current TCEC Cup

Damir wrote:
Fri Oct 19, 2018 3:35 pm
I change my prediction to 4-1 for Stockfish. 3 wins and 2 draws. :) :) :D
Match over, 4.5-2.5 as I predicted as likely.
by jkiliani
Fri Oct 19, 2018 2:55 pm
Forum: Computer Chess Club: General Topics
Topic: Current TCEC Cup
Replies: 22
Views: 3373

Re: Current TCEC Cup

Stockfish will win 6:2. Lc0 does not stand a chance :) :) :D Apart from being impossible as was already pointed out, it would also be highly optimistic from SF's view. Likely outcomes are 4.5-3.5, 5-3 and 4.5-2.5. Worse scores than this for Leela are not likely since Lc0-SF with the current net has...
by jkiliani
Tue Oct 02, 2018 3:11 pm
Forum: Computer Chess Club: General Topics
Topic: Lc0 v18 rc2 for 2080 Syzygy implementation
Replies: 34
Views: 5233

Re: Lc0 v18 rc2 for 2080 Syzygy implementation

I tested yesterday on 100 long 6-men draws (not sure if they are exactly hard, but many of them are), no losses. Avoiding TB losses against non-TB engine needs comparison with another Syzygy-enabled engine against that non-TB engine. Might compare Lc0_Syzygy against SF8_no_TB compared to SF8_Syzygy...
by jkiliani
Tue Oct 02, 2018 1:06 pm
Forum: Computer Chess Club: General Topics
Topic: Lc0 v18 rc2 for 2080 Syzygy implementation
Replies: 34
Views: 5233

Re: Lc0 v18 rc2 for 2080 Syzygy implementation

How about fixing a bug where engine will suddenly resign during the game out of nowhere? This happens during draw or won game, and especially in long games... To fix bugs, we need to first reproduce them. Can you give a .pgn file where this happened for you, as well as specifics about the binary yo...
by jkiliani
Tue Oct 02, 2018 11:12 am
Forum: Computer Chess Club: General Topics
Topic: Lc0 v18 rc2 for 2080 Syzygy implementation
Replies: 34
Views: 5233

Re: Lc0 v18 rc2 for 2080 Syzygy implementation

No misses this time on 100 hard 6-men wins. Maybe I will check on say 200 other 6-men won positions, but it seems fine now. Great, thank you for the whole Leela Dev team! Do you have any testing suites about holding difficult draws, or avoiding losses on TB lost positions against opponents without ...