Topic+ why there isn’t analysor engines such as stockfish in chess, for go.
Probably there’s some information here
opened 01:57PM - 16 Dec 19 UTC
Hi all,
there's 500k games now without a network promoting. This means the tr… aining window is "full". I increased it to 750k games, and did a last learning rate lowering (0.00001 @ bs=96). If this doesn't result in a promotion, we've pretty much reached the end of the first training run, after just over 2 years.
As I stated before, I don't have enough time nor energy to contribute any more (Leela Zero was very successful and achieved much more than I set out for, but it also ate a lot of my time especially the first year...) so I will not set up a second training run myself. There's many options to go from here, from someone picking and choosing the most promising improvements that have been proposed here and elsewhere to do a Leela Zero 2.0, to joining the community behind one of the other initiatives that built upon what we started (obviously SAI, but I heard KataGo is considering setting up a distributed effort as well).
I plan to keep the training server running until the 31st of January (if necessary bumping the playout count to add some more high quality data to the pool). If the last learning rate drop miraculously sends us improving again, I can extend that, but for now I would say that the community should probably plan its next steps with that date in mind.
5 Likes
Have you heard of KataGo?
4 Likes
Katago basically took over the number one spot for analysis engine in Western countries. There are others but mostly people use Kata for analysis. It’s stronger than Leela, also free and runs with Lizzie and Sabaki. There’s alao Katrain which integrates Kata with it’s GUI.
8 Likes