Life In 19x19 http://lifein19x19.com/ |
|
Leela has a new version http://lifein19x19.com/viewtopic.php?f=18&t=13251 |
Page 4 of 7 |
Author: | pookpooi [ Sun Feb 19, 2017 10:36 am ] |
Post subject: | Re: Leela has a new version |
Can you produce more game between them? Like 9 more matches so that we can measure how good leela is against other bot on the same hardware |
Author: | Gomoto [ Sun Feb 19, 2017 10:59 am ] |
Post subject: | Re: Leela has a new version |
It is fun to watch strong players (Zenith and Leela). But I am not quite sure it is that much fun. |
Author: | Pippen [ Sun Feb 19, 2017 4:55 pm ] |
Post subject: | Re: Leela has a new version |
Leela lacks a self-play modus. |
Author: | pookpooi [ Mon Feb 20, 2017 1:37 am ] |
Post subject: | Re: Leela has a new version |
Gomoto wrote: It is fun to watch strong players (Zenith and Leela). But I am not quite sure it is that much fun. Leela 0.9 is now on cgos so we'll know tomorrow if it's stronger than zen or not |
Author: | yharzu [ Mon Feb 20, 2017 2:32 am ] |
Post subject: | Re: Leela has a new version |
pookpooi wrote: Leela 0.9 is now on cgos so we'll know tomorrow if it's stronger than zen or not ah, cool. Can you keep us up to date? |
Author: | Garf [ Mon Feb 20, 2017 3:57 am ] |
Post subject: | Re: Leela has a new version |
Pippen wrote: Leela lacks a self-play modus. gogui can do this I believe - shame it's not developed any more. |
Author: | Garf [ Mon Feb 20, 2017 4:09 am ] |
Post subject: | Re: Leela has a new version |
pookpooi wrote: Leela 0.9 is now on cgos so we'll know tomorrow if it's stronger than zen or not Are CGOS ratings reliable? 3 Zen-13.1-1c0g 3791 88 88 252 94% 3143 0% 4 Zen-13.3-1c0g 3762 51 51 500 89% 3159 0% ... 11 Zen-13.7-1c0g 3676 49 49 582 90% 3002 0% 13 Zen-13.9-1c0g 3645 43 43 486 74% 3219 0% 14 Zen-13.8-1c0g 3637 70 70 259 88% 3001 0% Zen's authors should stop developing it, every new version is getting weaker 72 Leela-0.8.0-4c1g 3162 76 76 217 60% 2906 0% 73 Leela-0.7.0-4c 3154 79 79 213 71% 2642 0% No real difference and older version wasn't even using GPU. Leela's author should also stop "improving" it 29 Rn.3.6-4c 3439 70 70 215 71% 2968 0% 30 Rn.3.7-4c 3430 45 45 523 70% 2985 0% 32 Rn.3.3-4c 3426 29 29 1200 65% 3011 0% 33 Rn.3.5-4c 3411 68 68 204 68% 3006 0% 43 Rn.3.4.1-4c 3360 65 65 201 59% 3113 0% 49 Rn.3.8-4c 3295 71 71 229 65% 2889 0% "Rn" author seems to have found the trick after a lot of trying because Rn.3.9 was finally rated higher. I don't know what causes this but either CGOS is not reliable or authors of Go bots have no idea what they are doing. |
Author: | pookpooi [ Mon Feb 20, 2017 5:16 am ] |
Post subject: | Re: Leela has a new version |
My interpretation is that Zen developers failed to improve after 13.3, that's why they push 13.3 1c1g (to try to see if gpu implement correctly) and will probably use this version in March big matches. There's currently 3 Zen version running on cgos now, 13.3 1c1g, 13.9 1c1g (just in case if gpu implement will be super effective that will surpass 13.3, which sadly it isn't) and 12.0 1c0g as anchor. |
Author: | Garf [ Mon Feb 20, 2017 5:16 am ] | ||
Post subject: | Re: Leela has a new version | ||
I think your Leela just beat the very latest Zen, who's also using GPU acceleration?
|
Author: | Garf [ Mon Feb 20, 2017 5:24 am ] |
Post subject: | Re: Leela has a new version |
pookpooi wrote: My interpretation is that Zen developers failed to improve after 13.3. 12.5 is actually the highest rated one. Very sad that Zen didn't improve, then, but I do wonder if it's really true. Code: 1 Zen-12.5n-1c1g 3815 147 147 188 97% 2768 0%
2 Zen-13.1-0.5-1c0g 3799 52 52 881 95% 3069 0% 3 Zen-13.1-1c0g 3791 88 88 252 94% 3143 0% 4 Zen-13.3-1c0g 3762 51 51 500 89% 3159 0% |
Author: | pookpooi [ Mon Feb 20, 2017 5:27 am ] |
Post subject: | Re: Leela has a new version |
13.3 1c1g is not in BayesElo page yet, you can find it here http://www.yss-aya.com/cgos/19x19/standings.html I think it'll appear tomorrow. |
Author: | johnsmith [ Tue Feb 21, 2017 1:07 am ] |
Post subject: | Re: Leela has a new version |
0.9.0 is stronger than Zen in my personal opinion. One interesting thing: neural net gives around 36-37% at 3 handicap stones and 0.5 komi, but if you increase komi to 10.5, % will be much lower. The same thing happens in even game with/without komi. Why is that? |
Author: | Uberdude [ Tue Feb 21, 2017 2:40 am ] |
Post subject: | Re: Leela has a new version |
johnsmith wrote: 0.9.0 is stronger than Zen in my personal opinion. Do you mean the latest commercially available version (about 6d ama strength) or the latest on KGS/Tygem (about mid pro strength)? |
Author: | pookpooi [ Tue Feb 21, 2017 2:53 am ] |
Post subject: | Re: Leela has a new version |
We'll know it tomorrow, but the comparison is not quite fair cause Leela 0.9.0 is 1c1g while Zen 11.4 (aka Zenith Go 6) is only 1c (gpu not supported yet). From what I look like now it's close. |
Author: | johnsmith [ Tue Feb 21, 2017 4:36 am ] |
Post subject: | Re: Leela has a new version |
Uberdude wrote: johnsmith wrote: 0.9.0 is stronger than Zen in my personal opinion. Do you mean the latest commercially available version (about 6d ama strength) or the latest on KGS/Tygem (about mid pro strength)? I meant Zen6 (7 dan). Because in a couple of games Zen was saying it was even (around 50%), while Leela's neural net % was extremely high (80%) and MC % was like Zen's. In 10-15 moves, Zen's estimate dropped down to 35%. |
Author: | Garf [ Wed Feb 22, 2017 1:00 pm ] |
Post subject: | Re: Leela has a new version |
Code: 50 Leela-0.9-1c1g 3320 107 107 154 67% 2935 0% 62 Zen-11.4n-1c 3244 40 40 633 71% 2861 0% 76 ELO ahead of the commercial Zen So Leela (with GPU) is between half a stone and a stone stronger than Zenith Go 6. johnsmith called it, Gomoto was wrong. |
Author: | goame [ Wed Feb 22, 2017 1:17 pm ] |
Post subject: | Re: Leela has a new version |
Garf wrote: Code: 50 Leela-0.9-1c1g 3320 107 107 154 67% 2935 0% 62 Zen-11.4n-1c 3244 40 40 633 71% 2861 0% 76 ELO ahead of the commercial Zen So Leela (with GPU) is between half a stone and a stone stronger than Zenith Go 6. johnsmith called it, Gomoto was wrong. Is it possiple to use 4x nvidia geforce gtx 1080 ti with Leela? And how big is the benefit from 1 to 2 to 4 gpus? |
Author: | Garf [ Wed Feb 22, 2017 1:19 pm ] |
Post subject: | Re: Leela has a new version |
goame wrote: Is it possiple to use 4x nvidia geforce gtx 1080 ti with Leela? No, because you cannot buy those yet |
Author: | pookpooi [ Wed Feb 22, 2017 6:30 pm ] |
Post subject: | Re: Leela has a new version |
It's hard to compare between Zen 6 (11.4) and Leela 0.9 in cgos, While Leela 1c1g is above Zen 1c by 76 elo, it's below Zen 2c by 77 elo. We need Leela without GPU (maybe 1 or 2 c or both) to have a better comparison. |
Author: | yoyoma [ Wed Feb 22, 2017 7:31 pm ] |
Post subject: | Re: Leela has a new version |
I saw somewhere (compgo?) that the Leela author said he is not running Leela on CGOS. So it is an unofficial test by someone else. |
Page 4 of 7 | All times are UTC - 8 hours [ DST ] |
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group http://www.phpbb.com/ |