Re: LCZero update
Posted: Sat Mar 17, 2018 1:53 am
Probably need to wait at least a week before those games become watchable Watching some of the training games hurt my eyes
I also matched it against TSCP, but it's still too much for Leela. It's 1700 elo and it will take a couple of weeks to reach that. i did pair it against the latest Sabrina (around 1350 elo) and it was drawing almost every match. You may try that one.pferd wrote:I upped the playouts to 150000 (equals 30-40s/move on my machine) and had a quick match against TSCP 1.81b which was using 1 min/game. The network in use was 1aa02cb1. The game with Leela using the white pieces did not look too bad for :CMCanavessi wrote:Playouts play a HUGE role in strenght. All the games I've been running use the default 800, which makes it rather weak but is good for the training purposes, as it provides more games/time. I see you use 50000, that's a nice number and should make it much stronger.pferd wrote: Does anybody know how strength increases when the number of playouts is raised?
[pgn]
[Event "Computer Chess Game"]
[Site "brutus"]
[Date "2018.03.16"]
[Round "1"]
[White "lczero"]
[Black "tscp"]
[Result "0-1"]
[TimeControl "60"]
[Annotator "1. -0.04 1... -0.30"]
1.d4
{-0.04/25}
1...d5
{-0.30/6 2.0}
2.Nf3
{-0.10/26 34}
2...Nf6
{-0.25/6 1.9}
3.c3
{-0.12/26 33}
3...Nc6
{+0.02/6 1.9}
4.b4
{-0.34/26 39}
4...e6
{+0.27/6 1.8}
5.a4
{-0.18/26 38}
5...Bd6
{+0.89/5 1.7}
6.Qd2
{-0.01/26 40}
6...O-O
{+1.02/6 1.7}
7.Qb2
{-0.05/26 41}
7...Bd7
{+0.92/6 1.6}
8.b5
{+0.03/26 41}
8...Ne7
{+0.81/6 1.6}
9.Ne5
{-0.04/26 41}
9...Bxe5
{+1.47/6 1.5}
10.dxe5
{-0.14/26 40}
10...Ng4
{+1.48/6 1.5}
11.Na3
{-0.49/26 39}
11...Nxe5
{+1.92/5 1.4}
12.g3
{-0.53/26 34}
12...c5
{+2.06/5 1.4}
13.f4
{+0.05/26 37}
13...Ng4
{+1.94/6 1.3}
14.e3
{+0.23/26 40}
14...e5
{+2.00/5 1.3}
15.Be2
{+0.17/26 40}
15...Qa5
{+1.83/6 1.2}
16.Nb1
{+0.84/26 40}
16...exf4
{+2.06/5 1.2}
17.exf4
{+1.21/26 42}
17...Rfe8
{+1.93/5 1.2}
18.Nd2
{+1.73/26 40}
18...Nf5
{+1.82/5 1.1}
19.Nb3
{+2.56/26 41}
19...Qb6
{+1.87/5 1.1}
20.O-O
{+1.40/26 40}
20...c4+
{+3.67/5 1.1}
21.Nd4
{+1.31/26 42}
21...Nxd4
{+3.67/5 1.0}
22.Bxg4
{-1.92/26 41}
22...Ne2+
{+4.80/5 1.0}
23.Kg2
{-1.64/26 40}
23...Bxg4
{+4.92/5 0.9}
24.Re1
{-1.53/26 40}
24...d4
{+5.55/5 0.9}
25.cxd4
{-2.47/26 40}
25...c3
{+5.59/4 0.9}
26.Qb3
{-2.54/26 39}
26...Qxd4
{+5.96/4 0.9}
27.Rd1
{-3.52/26 40}
27...Qe4+
{+99.93/5 0.4}
28.Kf2
{-28.77/20 2.2}
28...Qf3+
{+99.95/4 0.1}
29.Ke1
{-36.14/19 0.7}
29...Nxc1+
{+99.97/3 0.1}
30.Qe6
{-41.03/18 0.5}
30...Rxe6#
{Xboard adjudication: Checkmate}
0-1
[/pgn]
The reverse game however, was very hard to watch with Leela blundering a knight on move 2.
[pgn][Event "Computer Chess Game"]
[Site "brutus"]
[Date "2018.03.16"]
[Round "2"]
[White "tscp"]
[Black "lczero"]
[Result "1-0"]
[TimeControl "60"]
[Annotator "1. +0.13 1... +0.26"]
1.e4
{+0.13/6}
1...Nc6
{+0.26/25 36}
2.d4
{+0.22/6 1.9}
2...Nxd4
{+0.28/26 37}
3.Qxd4
{+2.30/6 1.9}
3...Nf6
{-0.09/26 31}
4.e5
{+3.00/5 1.8}
4...Ng8
{-0.74/26 38}
5.Nc3
{+2.90/5 1.7}
5...f6
{-0.47/26 36}
6.Bc4
{+2.93/5 1.7}
6...b5
{-0.27/26 38}
7.Bxg8
{+5.41/5 1.6}
7...Bb7
{-1.66/26 38}
8.Bd5
{+5.55/5 1.6}
8...c6
{-1.40/26 38}
9.Bf3
{+5.52/5 1.5}
9...Qb8
{-1.74/26 35}
10.Bf4
{+5.93/5 1.5}
10...d6
{-1.74/26 41}
11.exd6
{+6.05/5 1.4}
11...exd6
{-1.75/26 40}
12.O-O-O
{+6.24/4 1.4}
12...h5
{-2.49/26 39}
13.Qe4+
{+6.73/4 1.3}
13...Kf7
{-1.77/26 42}
14.Nxb5
{+6.82/5 1.3}
14...d5
{-3.61/26 40}
15.Qf5
{+7.32/5 1.2}
15...Qd8
{-3.88/26 40}
16.Nc7
{+7.88/5 1.2}
16...Bc5
{-3.90/26 40}
17.Bxh5+
{+9.43/4 1.2}
17...Kg8
{-7.72/26 40}
18.Qe6+
{+9.59/5 1.1}
18...Kh7
{-7.84/26 41}
19.Bf7
{+9.59/4 1.1}
19...g5
{-6.83/26 38}
20.Qf5+
{+13.27/5 1.0}
20...Kg7
{-8.59/26 39}
21.Qg6+
{+13.32/5 1.0}
21...Kf8
{-12.91/26 34}
22.Ne6+
{+13.37/5 1.0}
22...Ke7
{-13.06/26 33}
23.Nxd8
{+16.17/5 0.9}
23...Bxf2
{-13.17/26 32}
24.Qg7
{+17.10/5 0.9}
24...Be3+
{-13.91/25 36}
25.Bxe3
{+21.65/5 0.9}
25...Raxd8
{-14.22/25 37}
26.Bxd5+
{+23.96/4 0.9}
26...Kd6
{-17.83/25 36}
27.Bg8+
{+23.96/4 0.8}
27...Ke5
{-18.43/25 34}
28.Bd4+
{+25.32/5 0.8}
28...Rxd4
{-17.34/25 33}
29.Re1+
{+99.93/5 0.4}
29...Kf4
{-23.48/24 16}
30.Qxf6+
{+99.95/4 0.1}
30...Kg4
{-26.04/23 1.4}
31.Qf3+
{+99.97/3 0.1}
31...Kh4
{-40.26/18 1.1}
32.Qh3#
{Xboard adjudication: Checkmate}
1-0
[/pgn]
Maybe I was bit too optimistic, but let's see where this will go. Interesting days ahead for us.
Yep, but training games are not meant to be good yet, they are just meant to be fast. That's why they are played with a crippled Leela.CheckersGuy wrote:Probably need to wait at least a week before those games become watchable Watching some of the training games hurt my eyes
True. However, over at LeelaZero (Go-Engine) training games became watchable after some time despite the randomness that is used to encourage exploration. So I assume that things like blundering a knight on move 2 wont happenCMCanavessi wrote:Yep, but training games are not meant to be good yet, they are just meant to be fast. That's why they are played with a crippled Leela.CheckersGuy wrote:Probably need to wait at least a week before those games become watchable Watching some of the training games hurt my eyes
Hi Gary, when I visit that page it is not clear how I can contribute GPU time to the project. the page is missing a 'call to action' button. add a green button which says 'Get involved' which links to the client software and includes instructions.gladius wrote: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/
Yes, the website is kind of a mess because things are changing all the time. If you check a couple of messages above, I uploaded a package ready to use.Jesse Gersenson wrote:Hi Gary, when I visit that page it is not clear how I can contribute GPU time to the project. the page is missing a 'call to action' button. add a green button which says 'Get involved' which links to the client software and includes instructions.gladius wrote: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/
In the current .7z file LCZero/Setup_Training.bat includes a typo:
echo Tun.bat will be started once you press Enter
should be
echo Train.bat will be started once you press Enter
It doesn't have to be powerful, currently it just runs on the previously created network and produce game results, upload them and then they run the training based on everyone's results and create a new network.Werewolf wrote:Is a GeForce 10, 1060 any good for training?
I have one of those. I also have an older Quadro 5000 but it's not as powerful.