For anyone curious, LZ progress continues unabated. While the increase to 20-block nets didnāt yield an initial strength improvement, predictions that the increased network size would allow for further improvement seem to have been correct. There have now been 2 natural promotions of stronger net-to-net trained Leelas with a self-play Elo approaching 12000.
Interestingly, thereās also an incredibly strong 40-block network thatās been trained from a combo of the Elf and Leela games, which is on par with the new version of Elf for strength. While the project isnāt quite ready to switch from 20-block networks to 40-block networks just yet, in part because 40-block networks are twice as slow, game data generated by the 40-block network will be used to speed up progress in the 20-block series, in a similar manner to how Elf data is being used.
I am not sure if everybody realises, but Google removed ladder knowledge in Zero, just to show it can self-learn all concepts including ladders. Not because technically it is better, but because it is more beautiful / elegant in terms of self-learning.
The Master version, had the concept of what moves where ladder breakers and ladder captures. Here is the original feature information, the information what goes into Masterās network to determine what are good moves, and who is ahead:
The Leela-Zero creator, has copied googleās method as close as it could. But there is nothing (technically) restricting to create a Leela-Almost-Zero version, who is ladder aware.
So, not being able to read ladders is a design choice, not a restriction because of some technique or method.
Iām not sure, I would call it āremoved ladder knowledgeā. There are 2 input layers telling the neural network where ladders are and how to capture/escape them.
What is the remaining knowledge, the network has to learn about ladders?
LZ is probably near AG Master in strength. See Deepmindās chart below, where the x axis is the number in millions of self-play games. LZ is currently at 11.4 million self-play games. Since LZ uses the same algorithms as AGZ, more or less, the growth should be at least ballpark.
I have a question for those who know Leela Zero and also Leela 0.11
I asked in another thread too but had no response.
So, if you think itās OT here, please post your answer there:
What exactly āplayoutsā means for LZ? Is the same as ānodesā or āsimulationsā on Leela?
I can see Leela change its mind about the ābest moveā while doing more and more simulations, so I let it run for tens of thousands (30k, 50k, even more) on a single move before considering that done.
On LZ I can see people talking about 200 / 800 / 1000 playouts, so Iām not sure I understand correctly.
I believe the only difference with old-fashioned Monte Carlo Tree Search is the method by which it selects the next node to explore. In āclassicā MCTS this is done by a relatively easy function that looks at how much some node has been explored and how well itās chances are, but for LZ this is done by a function that uses a neural network, that is trained to spot the best move. It also uses the neural network to do the simulation, where it keeps playing until the game is decided and then updates the parent nodes. In classic MCTS this is often done randomly, or using heuristics that arenāt based on deep learning.
So then a playout is just the same as a simulation, but the thing with LZ is that it uses a much more complicated neural net, and thus one playout takes a lot more time (but is way more accurate).