Page 1 of 27
LCZero update
Posted: Wed Mar 14, 2018 5:30 am
by gladius
We have kicked off the reinforcement learning phase, where the network starts from random, and learns from self-play games.
The server is up at
http://162.217.248.187/, with over 280,000 games played so far. Huge thanks to all the people donating their machine time! We are up almost 2,000 elo from random play. The fun part is these games are totally unlike a traditional weak alpha-beta searcher. See some examples games from a user page, like this:
http://162.217.248.187/user/GaryS (not actually me
.
People have been running it in tournaments against things like SF level 0 version to try and gauge the strength. It's just getting strong enough to actually start to measure. Here is an example tournament from zz4032:
Code: Select all
# PLAYER : RATING ERROR POINTS GAMES WINS(%) WON DRAWN LOST DRAWS(%)
1 Stockfish8_level20_1min/game : 3355 ---- 210.5 400 52.6 60 301 39 75.2
8 Stockfish8_level3 : 1381 97 402.0 800 50.2 396 12 392 1.5
9 Stockfish8_level0 : 996 104 807.5 1200 67.3 805 5 390 0.4
10 lczero_7f8f_playouts3300 : 532 115 26.5 400 6.6 26 1 373 0.2
11 lczero_b91f_playouts3300 : 263 146 6.0 400 1.5 6 0 394 0.0
Re: LCZero update
Posted: Wed Mar 14, 2018 7:35 am
by Jhoravi
Hi. I explored some games on the given link
http://162.217.248.187/user/GaryS But the blunderfeasted games are nowhere near 2000 elo IMO. Am I missing something?
Re: LCZero update
Posted: Wed Mar 14, 2018 7:38 am
by Ozymandias
In that tournament, I see lczero_7f8f_playouts3300 with a performance of 532, and you say its Elo is approximately 2,000 points ahead of random play. That either means getting some negative Elo values, or some seriously inflated assumptions (probably tracing back all the way to human chess).
Re: LCZero update
Posted: Wed Mar 14, 2018 7:41 am
by Ozymandias
Jhoravi wrote:Hi. I explored some games on the given link
http://162.217.248.187/user/GaryS But the blunderfeasted games are nowhere near 2000 elo IMO. Am I missing something?
He's not saying that they're at a 2,000 Elo level, they're 2,000 Elo points ahead of random play. Now the question would be, what's the Elo for a random player?
Re: LCZero update
Posted: Wed Mar 14, 2018 11:48 am
by Milos
Ozymandias wrote:Jhoravi wrote:Hi. I explored some games on the given link
http://162.217.248.187/user/GaryS But the blunderfeasted games are nowhere near 2000 elo IMO. Am I missing something?
He's not saying that they're at a 2,000 Elo level, they're 2,000 Elo points ahead of random play. Now the question would be, what's the Elo for a random player?
Since random play is certainly not 5000 Elo weaker than SF, the only logical assumption is that initial LCZero was much weaker than random play.
Authors should have maybe thought of using it for suicide chess
.
Re: LCZero update
Posted: Wed Mar 14, 2018 11:49 am
by Uri Blass
Ozymandias wrote:Jhoravi wrote:Hi. I explored some games on the given link
http://162.217.248.187/user/GaryS But the blunderfeasted games are nowhere near 2000 elo IMO. Am I missing something?
He's not saying that they're at a 2,000 Elo level, they're 2,000 Elo points ahead of random play. Now the question would be, what's the Elo for a random player?
202 elo based on CCRL 40/4
http://www.computerchess.org.uk/ccrl/40 ... t_all.html
Re: LCZero update
Posted: Wed Mar 14, 2018 11:59 am
by Uri Blass
From CCRL:
LaMoSca 0.10-Brutus RND 10.5-9.5(only one win for LaMoSca)
Ram 2.0-Brutus RND 20-0
Ram 2.0-LaMoSca 0.10 11.5-9.5(only 2 wins for Ram)
Without seeing the games I suspect that LaMoSca is one of the program that should be removed from CCRL because it artificially increase the rating of the random player.
Probably LaMoSca is relatively strong in the opening but later allow stalemates or repetitions and without seeing the games I suspect that in most games it get a winning advantage against Ram 2.0 but translate it to a draw.
Re: LCZero update
Posted: Wed Mar 14, 2018 12:14 pm
by CheckersGuy
Milos wrote:Ozymandias wrote:Jhoravi wrote:Hi. I explored some games on the given link
http://162.217.248.187/user/GaryS But the blunderfeasted games are nowhere near 2000 elo IMO. Am I missing something?
He's not saying that they're at a 2,000 Elo level, they're 2,000 Elo points ahead of random play. Now the question would be, what's the Elo for a random player?
Since random play is certainly not 5000 Elo weaker than SF, the only logical assumption is that initial LCZero was much weaker than random play.
Authors should have maybe thought of using it for suicide chess
.
Impossible for lcZero to be weaker than random play
Re: LCZero update
Posted: Wed Mar 14, 2018 12:31 pm
by koedem
Why wouldn't random play be 5000 Elo weaker than SF? If we assume random play at -1500 Elo and SF at 3500 Elo (both seem reasonable) we get to a difference of 5000. Seems logical to me.
Re: LCZero update
Posted: Wed Mar 14, 2018 12:48 pm
by CMCanavessi
Uri Blass wrote:From CCRL:
LaMoSca 0.10-Brutus RND 10.5-9.5(only one win for LaMoSca)
Ram 2.0-Brutus RND 20-0
Ram 2.0-LaMoSca 0.10 11.5-9.5(only 2 wins for Ram)
Without seeing the games I suspect that LaMoSca is one of the program that should be removed from CCRL because it artificially increase the rating of the random player.
Probably LaMoSca is relatively strong in the opening but later allow stalemates or repetitions and without seeing the games I suspect that in most games it get a winning advantage against Ram 2.0 but translate it to a draw.
I have ran LaMoSca in my tournaments A LOT and it has an issue, it can't win (or maybe it was programed that way deliberately). It will not promote pawns, they will all remain in the 7th rank forever (except very rare cases where they can take a piece in the 8th rank). Its "real" strenght is around 800-1000 elo, but after capturing every piece of the oponent, it will 3-fold. That's why it will have a lot of draws, and no wins.