Announcing lczero

Discussion of anything and everything relating to chess playing software and machines.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Jhoravi
Posts: 256
Joined: Wed May 08, 2013 4:49 am

Re: Announcing lczero

Post by Jhoravi » Wed Jan 10, 2018 2:59 pm

gladius wrote:A pretty amusing training game :).

[pgn]
1. f3 d5 2. b3 c6 3. d3 Qd6 4. Bh6 Qxh6 5. Nh3 Qe6 6. Kf2 Qf5 7. Kg3 h5 8. Nf2
h4# {Black mates} 0-1
[/pgn]
I don't get why White didn't anticipate the simple h4# mate. Does it mean the training phase is only one ply deep?
Last edited by Jhoravi on Wed Jan 10, 2018 3:01 pm, edited 1 time in total.

Daniel Shawul
Posts: 3970
Joined: Tue Mar 14, 2006 10:34 am
Location: Ethiopia
Contact:

Re: Announcing lczero

Post by Daniel Shawul » Wed Jan 10, 2018 3:00 pm

I will be very curious to see how the MCTS + NN improve upon its tactical weakness.

I think If stockfish changes approach, it would only be to replace its evaluation with the NN while keeping the same search.

Those complaining about the match setup with the alphago have an obligation to become more productive and contribute CPU/GPU power :)

Thanks for doing this!

Daniel

gladius
Posts: 538
Joined: Tue Dec 12, 2006 9:10 am

Re: Announcing lczero

Post by gladius » Wed Jan 10, 2018 5:28 pm

Jhoravi wrote:
gladius wrote:A pretty amusing training game :).

[pgn]
1. f3 d5 2. b3 c6 3. d3 Qd6 4. Bh6 Qxh6 5. Nh3 Qe6 6. Kf2 Qf5 7. Kg3 h5 8. Nf2
h4# {Black mates} 0-1
[/pgn]
I don't get why White didn't anticipate the simple h4# mate. Does it mean the training phase is only one ply deep?
No, but it's limited to 800 nodes. And if the network doesn't think the mate is a likely move, it might not be explored. I probably need to tune the UCT exploration parameter for chess vs go (it's using the original Leela Zero value right now).

Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: Announcing lczero

Post by Rodolfo Leoni » Wed Jan 10, 2018 5:31 pm

cdani wrote:Nice! Congratulations!
I agree, Daniel, it's nice, but... how a mere mortal like me can help? And I'd eventually have my own learning engine, or my CPU time would help to build the learning stuff on remote?

Thanks to anybody who could clear my few and confused ideas... :D
F.S.I. Chess Teacher

Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: Announcing lczero

Post by Rodolfo Leoni » Wed Jan 10, 2018 10:09 pm

I'm trying it. It's self-playing something but I can't understand the output. It's something like

1 <B D4> 2 <W Q4> 3 <B R17> 4 <W Q16>.........

and so on.

Well, I'll let it run to understand it while eating.

Interesting. But is it chess? :lol:
F.S.I. Chess Teacher

Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: Announcing lczero

Post by Rodolfo Leoni » Wed Jan 10, 2018 11:03 pm

Rodolfo Leoni wrote:I'm trying it. It's self-playing something but I can't understand the output. It's something like

1 <B D4> 2 <W Q4> 3 <B R17> 4 <W Q16>.........

and so on.

Well, I'll let it run to understand it while eating.

Interesting. But is it chess? :lol:
LOL White won first game in 195 plies. No idea about the game anyway...
It'd be much more interesting if I could understand what happens...
F.S.I. Chess Teacher

gladius
Posts: 538
Joined: Tue Dec 12, 2006 9:10 am

Re: Announcing lczero

Post by gladius » Thu Jan 11, 2018 12:48 am

Rodolfo Leoni wrote:
Rodolfo Leoni wrote:I'm trying it. It's self-playing something but I can't understand the output. It's something like

1 <B D4> 2 <W Q4> 3 <B R17> 4 <W Q16>.........

and so on.

Well, I'll let it run to understand it while eating.

Interesting. But is it chess? :lol:
LOL White won first game in 195 plies. No idea about the game anyway...
It'd be much more interesting if I could understand what happens...
I think you are running leela-zero, not lczero. Leela-zero is the Go player, and those look like Go moves :).

lczero isn't quite ready for the distributed training portion yet, still working some bugs out of the system.

Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: Announcing lczero

Post by Rodolfo Leoni » Thu Jan 11, 2018 1:01 am

gladius wrote:
Rodolfo Leoni wrote:
Rodolfo Leoni wrote:I'm trying it. It's self-playing something but I can't understand the output. It's something like

1 <B D4> 2 <W Q4> 3 <B R17> 4 <W Q16>.........

and so on.

Well, I'll let it run to understand it while eating.

Interesting. But is it chess? :lol:
LOL White won first game in 195 plies. No idea about the game anyway...
It'd be much more interesting if I could understand what happens...
I think you are running leela-zero, not lczero. Leela-zero is the Go player, and those look like Go moves :).

lczero isn't quite ready for the distributed training portion yet, still working some bugs out of the system.
Thanks Gary. :D
I suspected it was about Go because "moves" made no sense. I just found the "Leela Zero release" folder and I was very curious. Enough to keep me awake.

There'll be a meeting of Federal Regional Council on next saturday and I'll speak about LeelaCZero project. I'm sure it'll be very interesting for everybody.
F.S.I. Chess Teacher

Jhoravi
Posts: 256
Joined: Wed May 08, 2013 4:49 am

Re: Announcing lczero

Post by Jhoravi » Thu Jan 11, 2018 2:27 pm

I found another similar project :D
https://github.com/Zeta36/chess-alpha-zero

Gian-Carlo Pascutto
Posts: 1196
Joined: Sat Dec 13, 2008 6:00 pm
Contact:

Re: Announcing lczero

Post by Gian-Carlo Pascutto » Thu Jan 11, 2018 2:32 pm

This happens a lot in the early (and sometimes later) training games in go as well. One player passes and doesn't realize the other one can win immediately by passing as well.

It will learn its way out of this.

Post Reply