http://lczero.org/
I am keen for an explanation.
Did anyone notice the 100 Elo explosion in LCZero?
Moderators: hgm, Rebel, chrisw
-
- Posts: 12545
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Did anyone notice the 100 Elo explosion in LCZero?
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 2564
- Joined: Fri Nov 26, 2010 2:00 pm
- Location: Czech Republic
- Full name: Martin Sedlak
Re: Did anyone notice the 100 Elo explosion in LCZero?
bigger networks
-
- Posts: 4611
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Did anyone notice the 100 Elo explosion in LCZero?
that was easy ;-)mar wrote:bigger networks
https://rwbc-chess.de
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
-
- Posts: 72
- Joined: Mon Mar 07, 2016 4:41 pm
- Location: Zürich, Switzerland
Re: Did anyone notice the 100 Elo explosion in LCZero?
I am playing it on a more or less regular basis in the easy mode (= as far as I can see just playing the move the policy network recommends without any search) - I am very impressed by what I see there. I have trouble beating it despite being a strong chess player, and I definitely do some calculations
I'm very curious to see how far this goes!
I'm very curious to see how far this goes!
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: Did anyone notice the 100 Elo explosion in LCZero?
wrong setup
Bigger network but tested with fixed nodes per moves
Bigger network but tested with fixed nodes per moves
-
- Posts: 2564
- Joined: Fri Nov 26, 2010 2:00 pm
- Location: Czech Republic
- Full name: Martin Sedlak
Re: Did anyone notice the 100 Elo explosion in LCZero?
Yes, you're right, +100 elo but 2x slower. Also self-play inflates about 2x.Daniel Shawul wrote:wrong setup
Bigger network but tested with fixed nodes per moves
But I'm running a test now and so far it seems much stronger than the last one I tested (217) even if it runs at half speed.
Still too early to draw conclusions but ID 217 scored 35% against 2CPU Cheng in 100 games,
now it's 47% but only 34 games, still it seems to work very well.
I'm really excited about this project, it will soon pass 3k CCRL on consumer hardware, looking forward to see next TCEC.
-
- Posts: 2873
- Joined: Wed Mar 08, 2006 10:09 pm
- Location: Germany
- Full name: Werner Schüle
Re: Did anyone notice the 100 Elo explosion in LCZero?
Yes,
the nps are about 50% lower under the same conditions.
So maybe not much difference in strenght.
the nps are about 50% lower under the same conditions.
So maybe not much difference in strenght.
Werner
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: Did anyone notice the 100 Elo explosion in LCZero?
Yes, I think the self-play is not done in timed games, but a fixed nodes or depth or whatever, so 100 Elo in self-play would mean it is not taking into account the slower speed that will reduce strength in timed games.Werner wrote:Yes,
the nps are about 50% lower under the same conditions.
So maybe not much difference in strenght.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 143
- Joined: Wed Jan 17, 2018 1:26 pm
Re: Did anyone notice the 100 Elo explosion in LCZero?
Correct, all self-play matches are done at fixed 800 nodes. The strength at fixed time controls is roughly similar right now between the new 192x15 net and the previous 128x10 network. Still, this makes sense for self-play Elo, since the gain will mean much higher quality of the training data from now on. Also, the new network size has a lot of growth potential and should be able to gain a couple hundred more Elo over the coming weeks.Albert Silver wrote:Yes, I think the self-play is not done in timed games, but a fixed nodes or depth or whatever, so 100 Elo in self-play would mean it is not taking into account the slower speed that will reduce strength in timed games.Werner wrote:Yes,
the nps are about 50% lower under the same conditions.
So maybe not much difference in strenght.
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: Did anyone notice the 100 Elo explosion in LCZero?
I wasn't complaining, just noting. The new 227 is about similar strength to the last editions of older NN, though a bit more boring to watch. Still, I expect that will change soon as it begins to take shape. Looking forward to it.jkiliani wrote:Correct, all self-play matches are done at fixed 800 nodes. The strength at fixed time controls is roughly similar right now between the new 192x15 net and the previous 128x10 network. Still, this makes sense for self-play Elo, since the gain will mean much higher quality of the training data from now on. Also, the new network size has a lot of growth potential and should be able to gain a couple hundred more Elo over the coming weeks.Albert Silver wrote:Yes, I think the self-play is not done in timed games, but a fixed nodes or depth or whatever, so 100 Elo in self-play would mean it is not taking into account the slower speed that will reduce strength in timed games.Werner wrote:Yes,
the nps are about 50% lower under the same conditions.
So maybe not much difference in strenght.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."