Some Questions about Lizzie/LZ

[Bill Spight]

Since LZ starts Black with only 46% chance I wonder at what value it thinks the game is still on equal terms. E.g. if you have a value of 35% do you still have chances in the eye of LZ or is it a lost game?

Recent research by Viktor Lin ( https://explorebaduk.com/2019/04/08/how ... -research/ ) suggests that a winrate difference of around 10% translates to a difference of about 2 points of area/territory. OC, as we approach 100% or 0% that does not hold up. You would only have to be 10 points behind for Leela Zero to think you had a lost game. OC, at amateur levels that is not so. But if Black started with a 46% winrate estimate and dropped to a 35% estimate, she has probably lost around 2 points of area/territory to par.

Here is a quote from the site:

For our research, we used Leela version 0.16 – 15 block trained on 40 blocks with Lizzie 0.7 and let it judge an artificial position in which one colour (White) controls a closed-off territory that can be adjusted without having to take into account additional factors, while leaving the rest of the board mostly open so that the position can still be considered as in the state of fuseki.

In order to ensure a fair Leela judgement for each position as best as possible, we let it go to roughly the same number of visits (50k) on the move that received the most visits.

Edit: OC, a 2 point territory/area difference becomes more significant towards the end of the game.