Re: TCEC season 13, 2 NN engines will be participating, Leela and Deus X
Posted: Wed Aug 01, 2018 5:48 pm
Computer Chess Club
https://talkchess.com/
No, the reason I'm using human games is because that was the idea from the beginning. To see how far the neural network could go from purely human games. Please note that the structure of this particular neural network is about 4 times smaller than the one submitted to TCEC by the Leela team (10161 I think).jorose wrote: ↑Wed Aug 01, 2018 5:11 pmI would imagine one of the primary reasons he is using "Human" games (I thought I read somewhere he is using correspondence games? If so, hardly human imo) is precisely because it uses several orders of magnitude less resources. Most of the resources required from those contributors were to create self play games, sometimes between absolute garbage quality networks. Each network is trained on a subset of those games, not all of them. If you do not have insane resources, like a distributed project or large company can have, then going the zero approach is not really feasible at the moment.
On the other hand I am not convinced you need too many games in order to train a network capable of producing much higher quality games than your dataset.
I was referring to the following links to your interview and a a statement from the leela team.Albert Silver wrote: ↑Wed Aug 01, 2018 5:42 pmIf you mean Chris Whittington's fountain of wisdom, I would question the use of the word 'information'.frankp wrote: ↑Wed Aug 01, 2018 5:24 pmThanks.jorose wrote: ↑Wed Aug 01, 2018 5:11 pmI would imagine one of the primary reasons he is using "Human" games (I thought I read somewhere he is using correspondence games? If so, hardly human imo) is precisely because it uses several orders of magnitude less resources. Most of the resources required from those contributors were to create self play games, sometimes between absolute garbage quality networks. Each network is trained on a subset of those games, not all of them. If you do not have insane resources, like a distributed project or large company can have, then going the zero approach is not really feasible at the moment.
On the other hand I am not convinced you need too many games in order to train a network capable of producing much higher quality games than your dataset.
I found some information on the leela forum site.
It is easy to think of the NN as just a very elaborate evaluation function, but it goes quite a bit deeper than that, and is the reason that some short-term moves, however forced, are permanently out of the reach of the NN whatever the depth or time spent. This is by no means to diminish the need and importance of a solid executable to run the MCTS and use the NN, but even tactics depend very much on the quality of the NN and how it was developed. The dataset I used was the same for over 8 tries, and some 2000 hours of computer time in all, yet 7 of those tries bombed, some quite badly. I invested a lot of time, hundreds of hours, testing, learning, preparing the material, reading god knows how many papers to try to find tweaks and improvements, and more. I have no regrets, and had plenty of fun, but it was a ton of work.frankp wrote: ↑Wed Aug 01, 2018 7:12 pmI was referring to the following links to your interview and a a statement from the leela team.Albert Silver wrote: ↑Wed Aug 01, 2018 5:42 pmIf you mean Chris Whittington's fountain of wisdom, I would question the use of the word 'information'.frankp wrote: ↑Wed Aug 01, 2018 5:24 pmThanks.jorose wrote: ↑Wed Aug 01, 2018 5:11 pmI would imagine one of the primary reasons he is using "Human" games (I thought I read somewhere he is using correspondence games? If so, hardly human imo) is precisely because it uses several orders of magnitude less resources. Most of the resources required from those contributors were to create self play games, sometimes between absolute garbage quality networks. Each network is trained on a subset of those games, not all of them. If you do not have insane resources, like a distributed project or large company can have, then going the zero approach is not really feasible at the moment.
On the other hand I am not convinced you need too many games in order to train a network capable of producing much higher quality games than your dataset.
I found some information on the leela forum site.
http://www.chessdom.com/statements-by-d ... o-authors/
https://www.youtube.com/watch?v=CpjvvcfbdR4
EDIT: just read the leela forum. No I was not referencing this, rather info provided through the leela chat. Forum was evidently the wrong word.
Do you plan on writing an article for CB, on how to train nets on your own? I would read it.Albert Silver wrote: ↑Wed Aug 01, 2018 3:43 pmChanging random numbers, as you suggest, would mean using some NN of Leela, instead of toiling on this for months as I have, building it from scratch, with numerous stalls and restarts along the way. Building a NN isn't that hard, but building a good one, much less a really good one, is very hard.
Sort of nature-nurture debate, I guess.Albert Silver wrote: ↑Wed Aug 01, 2018 7:55 pmIt is easy to think of the NN as just a very elaborate evaluation function, but it goes quite a bit deeper than that, and is the reason that some short-term moves, however forced, are permanently out of the reach of the NN whatever the depth or time spent. This is by no means to diminish the need and importance of a solid executable to run the MCTS and use the NN, but even tactics depend very much on the quality of the NN and how it was developed. The dataset I used was the same for over 8 tries, and some 2000 hours of computer time in all, yet 7 of those tries bombed, some quite badly. I invested a lot of time, hundreds of hours, testing, learning, preparing the material, reading god knows how many papers to try to find tweaks and improvements, and more. I have no regrets, and had plenty of fun, but it was a ton of work.frankp wrote: ↑Wed Aug 01, 2018 7:12 pmI was referring to the following links to your interview and a a statement from the leela team.Albert Silver wrote: ↑Wed Aug 01, 2018 5:42 pmIf you mean Chris Whittington's fountain of wisdom, I would question the use of the word 'information'.frankp wrote: ↑Wed Aug 01, 2018 5:24 pmThanks.jorose wrote: ↑Wed Aug 01, 2018 5:11 pmI would imagine one of the primary reasons he is using "Human" games (I thought I read somewhere he is using correspondence games? If so, hardly human imo) is precisely because it uses several orders of magnitude less resources. Most of the resources required from those contributors were to create self play games, sometimes between absolute garbage quality networks. Each network is trained on a subset of those games, not all of them. If you do not have insane resources, like a distributed project or large company can have, then going the zero approach is not really feasible at the moment.
On the other hand I am not convinced you need too many games in order to train a network capable of producing much higher quality games than your dataset.
I found some information on the leela forum site.
http://www.chessdom.com/statements-by-d ... o-authors/
https://www.youtube.com/watch?v=CpjvvcfbdR4
EDIT: just read the leela forum. No I was not referencing this, rather info provided through the leela chat. Forum was evidently the wrong word.
Lc0 training games are also full of mistakes, on purpose. The fact that one side played a mistake, and lost, is still information that can be leveraged.