![]() Supports board sizes ranging from 7x7 to 19x19, and as of May 2020 may be the strongest open-source bot on both 9x9 and 13x13 as well.Supports alternative values of komi (including integer values) and good high-handicap game play.Cares about maximizing score, enabling strong play in handicap games when far behind, and reducing slack play in the endgame when winning.Estimates territory and score, rather than only "winrate", helping analyze kyu and amateur dan games besides only on moves that actually would swing the game outcome at pro/superhuman-levels of play.KataGo's engine also aims to be a useful tool for Go players and developers, and supports the following features: Deep-Learning the Hardest Go Problem in the World.Blog posts about the initial release and some interesting subsequent experiments: Many thanks to Jane Street for supporting the training of KataGo's major earlier published runs, as well as numerous many smaller testing runs and experiments. These and a few research notes can be found here. Paper about the major new ideas and techniques used in KataGo: Accelerating Self-Play Learning in Go (arXiv).Ī few major further improvements have been found since then, which have been incorporated into KataGo's more recent runs. External data is not necessary for reaching top levels of play, but still appears to provide some mild benefits against some opponents, and noticeable benefits in a useful analysis tool for a variety of kinds of situations that don't occur in self-play but that do occur in human games and games that users wish to analyze. If tuned well, a training run using only a single top-end consumer GPU could possibly train a bot from scratch to superhuman strength within a few months.Įxperimentally, KataGo did also try some limited ways of using external data at the end of its June 2020 run, and has continued to do so into its most recent public distributed run, "kata1" at. ![]() As a result, early training is immensely faster than in other self-play-trained bots - with only a few strong GPUs for a few days, any researcher/enthusiast should be able to train a neural net from nothing to high amateur dan strength on the full 19x19 board. Some of these improvements take advantage of game-specific features and training targets, but also many of the techniques are general and could be applied in other games. KataGo was trained using an AlphaZero-like process with many enhancements and improvements, and is capable of reaching top levels rapidly and entirely from scratch with no outside data, improving only via self-play. KataGo's public distributed training run is ongoing! See for more details, to download the latest and strongest neural nets, or to learn how to contribute if you want to help KataGo improve further! Also check out the computer Go discord channel!Īs of 2023, KataGo remains one of the strongest open source Go bots available online. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |