Re: LCZero update
Posted: Fri Mar 16, 2018 4:28 pm
His problem with AlphaZero is that it dares to suggest that the current paradigm of chess engineering might not be the global optimum, which is an unforgivable affront to... something.
One thing to remember - the training games are played with randomization: https://github.com/glinscott/leela-ches ... #L169-L194. Eg. even if the search picks a good move, we can cause it to randomly select another one. This is done to ensure we explore more possibilities and every now and then that random selection will be better than the search, and the network will hopefully learn something .Uri Blass wrote:I look at the games and I see a lot of stupid one ply blunder that lose material.Leo wrote:Its logical to try LCZero to see if it works. I am skeptical but not a pessimist.
I do not know what they do but if after many thousands of games it plays like that then I do not believe in it.
I watched some of the games and at least the latest ones seem like it learned "something"gladius wrote:One thing to remember - the training games are played with randomization: https://github.com/glinscott/leela-ches ... #L169-L194. Eg. even if the search picks a good move, we can cause it to randomly select another one. This is done to ensure we explore more possibilities and every now and then that random selection will be better than the search, and the network will hopefully learn something .Uri Blass wrote:I look at the games and I see a lot of stupid one ply blunder that lose material.Leo wrote:Its logical to try LCZero to see if it works. I am skeptical but not a pessimist.
I do not know what they do but if after many thousands of games it plays like that then I do not believe in it.
So, the training games are not a good representation of the real strength of the network.
That being said, it will still blunder right now. Let's see where we are in a few months .
If it positively effects the performance then one might try that. However, I would stick with the usual scoring system as they are many other things that need to be worked on (Especially promoting the program to get more ppl involved). Restarting the training right now, doesn't seem wise.Robert Pope wrote:I was thinking - once LCZero is trained to a higher level, is it possible to train the weights to make draws less interesting? e.g. score draws as 0.3 instead of 0.5 to make it play more aggressively for a win?
Exeperience shows that draw level is not so low at the lowest human level of children and you often get stalemates.Vizvezdenec wrote:draw rate is low only because it plays on a level of 3-years old kid.
It certainly takes much more than an arrogant and delusional troll preaching them.David Xu wrote:So no, it does not simply have a low draw rate because it plays "like a three-year-old child". Wonder what it will take before you people start to understand.