I don't get why White didn't anticipate the simple h4# mate. Does it mean the training phase is only one ply deep?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]
Announcing lczero
Moderators: hgm, Rebel, chrisw
-
- Posts: 291
- Joined: Wed May 08, 2013 6:49 am
Re: Announcing lczero
Last edited by Jhoravi on Wed Jan 10, 2018 4:01 pm, edited 1 time in total.
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: Announcing lczero
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
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
-
- Posts: 568
- Joined: Tue Dec 12, 2006 10:10 am
- Full name: Gary Linscott
Re: Announcing lczero
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).Jhoravi wrote:I don't get why White didn't anticipate the simple h4# mate. Does it mean the training phase is only one ply deep?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]
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: Announcing lczero
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?cdani wrote:Nice! Congratulations!
Thanks to anybody who could clear my few and confused ideas...
F.S.I. Chess Teacher
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: Announcing lczero
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?
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?
F.S.I. Chess Teacher
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: Announcing lczero
LOL White won first game in 195 plies. No idea about the game anyway...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?
It'd be much more interesting if I could understand what happens...
F.S.I. Chess Teacher
-
- Posts: 568
- Joined: Tue Dec 12, 2006 10:10 am
- Full name: Gary Linscott
Re: Announcing lczero
I think you are running leela-zero, not lczero. Leela-zero is the Go player, and those look like Go moves .Rodolfo Leoni wrote:LOL White won first game in 195 plies. No idea about the game anyway...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?
It'd be much more interesting if I could understand what happens...
lczero isn't quite ready for the distributed training portion yet, still working some bugs out of the system.
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: Announcing lczero
Thanks Gary.gladius wrote:I think you are running leela-zero, not lczero. Leela-zero is the Go player, and those look like Go moves .Rodolfo Leoni wrote:LOL White won first game in 195 plies. No idea about the game anyway...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?
It'd be much more interesting if I could understand what happens...
lczero isn't quite ready for the distributed training portion yet, still working some bugs out of the system.
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
-
- Posts: 291
- Joined: Wed May 08, 2013 6:49 am
Re: Announcing lczero
I found another similar project
https://github.com/Zeta36/chess-alpha-zero
https://github.com/Zeta36/chess-alpha-zero
-
- Posts: 1243
- Joined: Sat Dec 13, 2008 7:00 pm
Re: Announcing lczero
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.
It will learn its way out of this.