| Life In 19x19 http://prod.lifein19x19.com/ |
|
| Flavoured weights http://prod.lifein19x19.com/viewtopic.php?f=18&t=17971 |
Page 1 of 1 |
| Author: | Ferran [ Fri Jan 01, 2021 9:11 am ] |
| Post subject: | Flavoured weights |
Has anyone compiled or trained weights with the characteristics of classic players? Games trained to follow the style of the Yasui school, for example; or Go Seigen. Take care |
|
| Author: | Ferran [ Fri Jan 15, 2021 9:49 am ] |
| Post subject: | Re: Flavoured weights |
Someone is already doing it with chess. I've only skimmed the abstracts, so far, but about 2000 games to train. We have as many games of some of the great players... https://lifein19x19.com/viewtopic.php?f ... ead#unread Take care |
|
| Author: | MikeKyle [ Sun Jan 17, 2021 7:20 am ] |
| Post subject: | Re: Flavoured weights |
I always assumed that even the most frequently playing pro with the longest career would not play enough games for an ai built using current techniques to learn from. Pleased to hear that I may be wrong. I've often wondered about making a takemiya-style centre-oriented bot by training using modified rules. Perhaps the rules could give an extra point to the owner of tengen? Or apply bonuses to a wider range of central points? Maybe the player with the most stones and or territory above the 4th line gets a bonus? I would be interested to see how much each incentive in the rules would make the bot play differently? |
|
| Author: | Bill Spight [ Sun Jan 17, 2021 7:50 am ] |
| Post subject: | Re: Flavoured weights |
MikeKyle wrote: I always assumed that even the most frequently playing pro with the longest career would not play enough games for an ai built using current techniques to learn from. Pleased to hear that I may be wrong. Learning by self play introduces path dependency. I would expect that today's AI bots could learn how to predict the plays of a specific player in short order, such that the predictions would generalize so that predictions in positions that the player never met are not just random. OC, the level of play of the bot at that point would be rather weak. Starting from that point the bot could be trained by self play to reach superhuman strength. Because of path dependency and, I believe, the likelihood that in most go positions there is more than one optimal play, I imagine that certain recognizable aspects of the player's style would be preserved in the bot's play. |
|
| Author: | Ferran [ Mon Jan 18, 2021 1:54 pm ] |
| Post subject: | Re: Flavoured weights |
It might be interesting to see what happens with players known to have changed styles. Would AI find a common theme? Take care. |
|
| Author: | hakuseki [ Mon Jan 18, 2021 9:48 pm ] |
| Post subject: | Re: Flavoured weights |
Training an AI to play like a (pre-AI era) 9-dan pro seems like a hard problem. If the AI is a pure policy with no search, then it is likely to misread many situations that the pro would read accurately. But the more you use search to correct the reading errors, the more it will tend to filter out the human-style moves that the value model judges suboptimal. Maybe an existing AI like KataGo could be run for a fixed number of iterations (e.g. 1000 visits) and its move evaluations could be used as an input feature for a new model trained to predict the human moves. |
|
| Page 1 of 1 | All times are UTC - 8 hours [ DST ] |
| Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group http://www.phpbb.com/ |
|