-
Other Go AI:
* [ ] https://senseis.xmp.net/?GoPlayingPrograms
* [ ] https://github.com/brilee/MuGo
- [ ] https://github.com/llSourcell/alphago_demo
* [ ] https://github.com/gcp/leela-zero
* […
-
Hi.
First of all, thank the team for this great project!
Now I am interested in whether Leela Zero have exceeded AlphaGo Zero or not yet.
I wonder it may be possible to know it if you analyze A…
y-ich updated
3 years ago
-
Hi,
Thanks for sharing your implementation of AlphaGo Zero.
I was wondering how long does it take to train AlphaGo-zero (RL based) on 9X9? And how long does it get?
Could you share which GPUs di…
-
# 五子棋 · AlphaGobang Zero - Yj-Zhang's Blog
五子棋 AlphaGo Zero Do you like to play Gobang ? Do you want to know how AlphaGo Zero works ? Check it out!
[https://youjiazhang.github.io/%E6%9C%BA%E5%99%A8%…
-
Leela Zero was developed on the basis of AlphaGo Zero, but we are constantly adding new technologies, such as: using fp16, using LCB, and possibly adding pull#2337, pull#2342, etc. in the future.
T…
LL145 updated
5 years ago
-
Of course that 20 block net has the fixed limit.
But I don't think that they moved to 40 block due to the limit of network.
(This opinion became popular after Hideki Kato which is developer of DeepZ…
-
Can you try to incorporate self-play technology similar to AlphaGo Zero?
-
C_puct needs to be tuned since it depends on a lot of other implementation details, and it's not given in the alphago zero paper.
I'm not sure if we're using the same momentum equations as alphago …
-
[Here you can see](https://github.com/MingWR/iceelz) someone created their own GUI like Lizzie and a feature I really liked in that is how they have the AlphaGo Master SGF as an opening book so that L…
-
在敲你的代码过程中遇到了两个问题，麻烦您给指导一下：
1. 根据AlphaGo Zero论文中的描述，在MCTS的backup过程中,首先根据policy-value network得到叶子节点的p，v，之后使用v来更新各个树内节点的Q值。在你的代码中使用的是函数update_recursive(leaf_value),这其中的leaf_value应该就是论文中该叶子节点的v对吧？为什么在mct…