ASilver

There is always give and take, so the balance between exploitation and exploration is obviously a complex one. I have done a lot of testing with the PUCT values to...

There is another thing worth adding: in the training games both sides get the same PUCT value, so you aren't really making it be stronger than itself, you are making...

Well, you can tune for matches or you can tune for learning.

I ran a small test to illustrate the difference. I took [a set of easy tactics](http://talkchess.com/forum3/viewtopic.php?f=2&t=67469) with single solutions and tested id302 on them with v10. Default settings (10 seconds...

I could be wrong of course, but I see a problem with using only a randomizer to hit on a tactic that it would not find otherwise: If it doesn't...

Ok, thanks for clarifying. I don't do a lot of tactics testing since I favor games, but there is zero question that this is the number one thing holding it...

_"I'd support a revert to 0.85, for the simple reason that we had tactically much stronger nets before introducing the PUCT change, and it would eliminate one more of the...

@killerducky I presume by graph, you mean the rating. I know the ratings are not directly comparable, since in a direct match NN237 (rated 5544), beats NN303 (rated 5710), by...

I certainly look forward to it. I have isolated a number of extreme misevaluations in king safety and closed positions (as extreme as +6 when it is more like 0.00)...

@killerducky I posted them in the forum here: https://groups.google.com/forum/#!topic/lczero/c1A5ioOv1K4 I also added the NN237 results in the last post of that thread. I can provide games and breakdown of results...