-
Hello!
Since it required huge amount of computing resources to teach network - is it possible to create some distributed system, where everyone who is willing can join and contribute their machine r…
-
hi,
**IMPORTANT UPDATE : 13 november 2018 !!!
TO ALL THOSE WHO USED THE GOOGLE CLOUD FREE TRIAL INSTRUCTIONS BEFORE 13 NOVEMBER 2018 :
https://docs.google.com/document/d/1P_c-RbeLKjv1umc4rMEgv…
-
@gcp,
can you shed some light on any concrete plans for Leela Zero and whether we will finally see (intrusive) features that go beyond what DeepMind has done (if only in an experimental pipeline)? …
-
您好！我在使用您的代码进行测试的时候（8*8棋盘），训练了4000轮达到了对于4000次模拟的纯蒙特卡洛算法10局全胜的结果，在与5000次模拟的蒙特卡洛算法中5胜5平。但是我在观察与传统五子棋引擎、人类与自我对弈的过程中，发现了两个问题：
1. 可能出现已经有明显的必胜的落子的走法时，选择不落在那里
2. 对于棋盘中还有较多可落子位置时，棋盘边缘的棋子，似乎根本不会考虑落子。。比如一开始就在…
-
As you know, there are some different approaches to utilize value network's evaluation.
For example, An open sourced computer go program RN, just averages value network evaluations and uses it, lik…
-
I've been able to compile CPU version `leelaz` on my Android phone with some small modifications (`local_storage` support has some problem with Android NDK, so I used `new` instead for a workaround, s…
-
Creating this topic because otherwise we'll see 10 identical issues pointing out the obvious.
It looks like 6x128 will have its last learning rate lowering soon. I've been training up 10x128 starti…
-
When I run parse.py, it always says found 0 chunks. Can you fix this?
-
In handicap games a human player would try to confuse the situation - by choosing moves with lots of variations, or maximizing the chance for the opponent to make mistakes. I am thinking LZ should be …
-
What we can learn from #1113, IMHO, is that a good net still buys us a lot of strength even with the same data. However, a good net is expensive in terms of compute power, and hence I was thinking if…